Seminar Assignment Summer 2023

The central registration for all computer science seminars will open on March 13th.

This system is used to distribute students among the available seminars offered by the CS department. To register for any of the seminars, you have to register here until April 12th, 23:59 CET. You can select which seminar you would like to take, and will then be automatically assigned to one of them on April 15th.

Please note the following:

  • We aim to provide a fair mapping that respects your wishes, but at the same time also respects the preferences of your fellow students.
  • Experience has shown that particular seminars are more popular than others, yet these seminars cannot fit all students.
  • Please only select seminars if you are certain that you actually do want to complete a seminar this semester. If you have already obtained sufficient seminar credits, or plan to take other courses this semester, feel free not to choose any seminars. Students who drop out of seminars take away places from those, who might urgently need a space or are strongly interested in the topic.
  • We encourage those students who wish to take a seminar this semester, to select their preferences for all available seminars, which eases the process to assign students that do not fit the overly popular seminars to another, less crowded one. So if you are serious about taking a seminar this semester, please select at least three seminars (with priority from "High" to "Low").
  • If you urgently need to be assigned to a seminar in the upcoming semester, choose at least five seminars (with priority from "High" to "Low"). We will then guarantee that you will be assigned to a seminar (yet not necessarily one of your choice).
  • If you are really dedicated to one particular seminar, and you do not want any other seminar, please select the "No seminar" as second and third positive option. However, this may ultimately lead to the situation that you are not assigned to any seminar. Also, choosing "No seminar" as second/third option does not increase your chances of getting your first choice.

The assignment will be automatically performed by a constraint solver on April 15th, 2023. You will be added to the respective seminars automatically and be notified about this shortly thereafter. Please note that the assignment cannot be optimal for all students if you drop the assigned seminar, i.e., make only serious choices to avoid penalty to others.


Accountable AI through the Lens of Causality by Goran Radanovic, Stelios Triantafyllou

Accountability is one of the pillars of trustworthy AI, and causality plays a pivotal role in defining concepts that are critical for enabling accountable decision processes in AI systems. In this seminar course, we will review recent advances in designing accountable AI agents, with emphasis put on designs that utilize casual reasoning. We will focus on the following three main topics: (i) actual causality and responsibility attribution, b) explainability and agents’ incentives, and c) accountability in reinforcement learning.

The course will be a combination of tutoring, presentation and discussion sessions. The students will be asked to write a report on state-of-the-art research papers on accountable AI. Although prior knowledge of casualty is not needed, basic understanding of decision making frameworks will be helpful.

Seminar website:

Requirements: This seminar is open to all BSc and MSc students, but priority will be given to students who have taken courses on AI and machine learning. We also ask students to provide us with a brief statement indicating their motivation for taking this seminar course, and explaining how this course relates to the projects they have undertaken in the past.

Places: 10

Advanced Cryptographic Primitives by Nico Döttling

In the last decades, cryptographic primitives have been developed which provide a broad range of functionalities and security features. For instance, the notion of identity-based encryption allows to send encrypted messages to a party who you have never interacted with and whose public key you don't know. In this seminar, we will explore a range of advanced cryptographic primitives which, at the time of their conception either solved long standing problems or opened up entirely new areas of cryptography.

Requirements: Having passed the core lecture "Cryptography" is mandatory for the participation in this seminar.

Places: 12

AI for Programming Education by Adish Singla

The course will provide an overview of state-of-the-art research on developing AI-driven educational technologies for introductory programming. The course consists of three main components as follows:

(1) Research papers: During the first half of the semester, students will be assigned 6-8 research papers and have to write a short report for each paper. These reports will be due during the semester, about one report per week.

(2) Project: During the second half of the semester, students will work on an implementation project.

(3) Final presentation: At the end of the semester, students will give a 25 mins presentation for one of the papers or the project.

This course is offered in the format of a block seminar, and there will be no weekly classes. We will schedule office hours where students can receive feedback on their projects.

Requirements: There are no formal requirements; however, please note the following points:

(1) Preference will be given to students who have already taken courses covering topics such as program analysis, natural language processing, educational technologies, software engineering, human-computer interaction, artificial intelligence, and machine learning.

(2) We are requesting you to provide a short motivation letter explaining the reasons why you are interested in taking this seminar. Please mention any relevant project(s) you have done. You can also mention all the relevant courses you have taken along with your grades. Please provide this information in the text box below.

Places: 8

AI for the Social Good by Verena Wolf, Gerrit Großmann, Kevin Baum

Are you an AI enthusiast eager to make a real difference beyond just theoretical knowledge? Do you aspire to use the latest AI technologies to tackle some of humanity's most pressing issues and make the world a better place? If so, we invite you to join us for "AI for the Social Good".
Our goal is to equip you with both theoretical and practical knowledge to create AI solutions to real-world problems. You'll have the opportunity to collaborate with other participants in a hands-on project to make a difference in your community or the world at large.

Requirements: While practical experience with AI is recommended, a broad interest in social challenges is also useful. If you've already completed "Ethics for Nerds," "AI for the Social Good" is the perfect course to put your knowledge into action.

Places: 15

Aspects of Quantitative Program Verification by Benjamin Kaminski, Lena Verscht

Are you passionate about logic, verification, semantics, and alike? Are you tired of thinking black-and-white, true-or-false? Then come and study the more nuanced quantitative formal program verification! In quantitative verification, properties are not just true or false. Instead, we verify quantities like runtimes, error probabilities, beliefs, etc.

Topics which we will cover include:

- Probabilistic programming (a currently trending modeling paradigm in machine learning),

- The geometry of neural networks

- Incorrectness logic (the latest creation of the former chief formal methods researcher at Facebook)

- The flow of quantitative information through programs

- Worst-case execution times

- Verification of heap-manipulating programs

- and many more

The seminar website can be found here:

Requirements: The most important requirement: You should really really like math and/or logic. This seminar covers very theoretical work.

The following courses are mandatory and/or recommended.

Mandatory: Programmierung 1, Programmierung 2, Grundzüge der Theoretischen Informatik

Recommended: Semantics; Introduction to Computational Logic; Automata, Games and Verification;

Ideal: Verification

Places: 12

Blockchains and Decentralized Finance (DeFi) by Johnnatan Messias and Krishna P. Gummadi

Blockchain technology is an increasingly popular decentralized ledger technology that utilizes a list of cryptographically linked records, called "blocks", to record transactions. This technology is used not only to create cryptocurrencies like Bitcoin but also to develop decentralized applications that run on top of Ethereum. In this seminar, we will delve into the design and implementation of blockchain technology, with a focus on its applications in Decentralized Finance (DeFi). We will cover four main topics: (i) background of blockchains, (ii) (Dis-)Incentives for Consensus, (iii) transaction prioritization, and (iv) Decentralized Finance (DeFi) applications.

The seminar website is available at

Requirements: This seminar is open to undergraduate and graduate students. A background in at least one of the following topics is required to participate in this seminar. Therefore, students must have passed one or more of these courses or an equivalent course:

- Operating Systems, Distributed Systems, or Networking
- Cryptography or Security-related courses
- Information Retrieval, Databases, Data Mining, Machine Learning, Data Science related courses

The course language is English. All lectures, office hours, presentations, and communication with the seminar staff will be conducted in English only.

Places: 15

Block Seminar Machine Learning for Natural Language Processing (Fall 2023) by Dietrich Klakow

Deep learning is the predominant machine learning paradigm in natural language processing (NLP). This approach not only gave huge performance improvements across a large variety of natural language processing tasks. However, large languages models struggle with rules, logic, reasoning and facts. Therefore this semesters seminar will focus on neuro-explicit models that is neural networks that also incorporate explicit knowledge like logic, math or laws of nature.

For more Information see

Places: 8

Computer-Assisted Proofs in LEAN by Laurent Bartholdi

As mathematical research advances, researchers become more and more specialized, and the mathematics they produce becomes more and more complicated to verify.
The possibility to formalize and check proofs thanks to computer programs is thus more relevant than ever. What’s more, tremendous progress in recent years make it so that formalizing actual research level mathematics is possible, and formalizing student level mathematics is accessible to students.
In this seminar, students will practice with the LEAN proof assistant (
We meet weekly on Zoom, and discuss informally: each student gets a chance to speak, to explain the work they have done in previous weeks, and to plan ahead.
See the course's page to obtain the zoom link.

Requirements: Students may obtain up to 8 credit points, by formalizing a theorem or new definitions, thus contributing to mathlib, the library which gathers all mathematics that has already been formalized in LEAN.
Topics suitable to both MSc and BSc students will be offered, no prior knowledge is required.

Places: 15

Computer Vision and Machine Learning for Computer Graphics by Christian Theobalt, Vladislav Golyanik, Mohamed Elgharib

Computer Vision strives to develop algorithms for understanding, interpreting and reconstructing information about real-world scenes from image and video data.

Computer Graphics focuses on image synthesis: algorithms to build and edit static and dynamic virtual worlds and to display them in photorealistic or stylized ways.

Machine Learning is concerned with studying and developing algorithms which use statistical models to solve problems by analyzing and drawing inference from data.

In recent years, these fields have converged more and more. Both Computer Vision and Computer Graphics create and exploit models describing the visual appearance of objects and scenes, while the most successful models heavily utilize ideas from Machine Learning. In this seminar series, we will cover advanced research topics that cross the boundaries between the fields of Computer Vision, Computer Graphics, and Machine Learning. This seminar will cover research papers from the following topics:

Image and video generation, manipulation, and analysis; multi-view geometry and reconstruction; computational photography and videography; shape matching; pose estimation, tracking, and character animation; deep learning for computer vision and computer graphics.

Seminar website:

Requirements: This seminar is aimed at graduate students in computer science or related fields.

Places: 12

Cryptographic Authentication by Lucjan Hanzlik

Authentication systems are crucial components in almost all areas of the digital world. They provide means for secure access control, privacy protection, and building trust between remote devices. We use those systems daily to log in to access emails, banking, and social media accounts, and even to access our smartphones and computers. We can authenticate ourselves remotely using modern electronic identification documents (eID), allowing us to use eGovernment services. We are often unaware that those systems are executed in the background between machines.

In this seminar, we will look at the cryptography behind authentication systems. Topics covered will include basic challenge-response authentication protocols, deniable authentication based on Diffie-Hellman key exchange, and authentication of eIDs and ePassports. We will also discuss privacy-preserving authentication mechanisms like group/ring signatures, anonymous credentials, and Privacy Pass.

Course organization:
-Kick-off meeting in the first week of the new semester
-One topic per person will be presented and discussed during 2-3 meetings on specific dates (TBD), i.e., the seminar will be in the form of a block course.

Requirements: Basic knowledge of security and cryptography.

Places: 12

Data-Driven Drug Design - Methods and Applications by Floriane Odje, Paula Kramer, Michael Backenköhler, Andrea Volkamer,

Introductory seminar on computer-aided drug design, including structure- and ligand-based methods. After a brief introduction, students will select a topic from the presented drug development pipeline and independently acquire knowledge on the selected topics in the context of structural bio- and cheminformatics.

Topics will include protein structure prediction, molecular docking, virtual screening, molecular fingerprints, chemical similarity, ADMET predictions, and QSAR; especially with increased focus on machine learning (ML) and deep learning (DL) methods.

Under guidance, material (papers, data, and algorithms) will be collected by each student and presented at the end of the seminar, including the implementation of an application of the individual topics.

Note: The seminar will be offered in parallel in Bioinformatics and Computer Science. The topics will be chosen to be either more algorithmic or application-oriented, so that students can choose topics according to their background, and at the same time will be introduced to the other focus through the talktorials of fellow students (see examples in our TeachOpenCADD platform:

Group website:

Date and Time: Tue's 10:15-11:45 during the semester (partly every other week)
Kick-off meeting: April 25th, 10:15 am, in person, CBI, room tbd.

Requirements: This seminar aims primarily at master students in computer science or related fields (note: bioinformatics students will have to register through a different system). Priority will be given to students who have successfully taken courses in programming, software development and/or machine learning. Familiarity with python and github are a must. Students should have had some intrinsic interest in biology, chemistry and/or physics, i.e. how computers can assist the drug design process.

We also ask students to provide us with a brief statement (half a page max) indicating their motivation for taking this seminar course, and explaining how this course relates to the projects they have undertaken in the past.

Places: 4

Data-driven Understanding of the Disinformation Epidemic (DUDE) by Yang Zhang

Arguably, one of the greatest inventions of humanity is the Web. Despite the fact it revolutionized our lives, the Web has also introduced or amplified a set of several social issues like the spread of disinformation and hateful content to a large number of people.

In this seminar, we will look into research that focuses on extracting insights from large corpus of data with the goal to understand emerging socio-technical issues on the Web such as the dissemination of disinformation and hateful content. We will read, present, and discuss papers that follow a data-driven approach to analyze large-scale datasets across several axes to study the multi-faceted aspects of emerging issues like disinformation.

During this seminar, the participants will have the opportunity to learn about state-of-the-art techniques and tools that are used for large-scale processing, including, but not limited to, statistical techniques, machine learning, image analysis, and natural language processing techniques.

Requirements: There are no formal prerequisites for this seminar. Despite this fact, it will be helpful if the participants have a basic understanding of machine learning.

Places: 12

Do we really need overparameterization in deep learning? by Rebekka Burkholz

Deep learning continues to impress us with breakthroughs across disciplines and is a major driving force behind a multitude of industry innovations like ChatGPT. Most of its successes are achieved by increasingly large neural networks that are trained on massive data sets and still achieve zero training loss. This recent trend to overparameterize neural networks defies classic concepts of statistical learning theory that suggest to avoid overfitting by reducing the number of trainable parameters. We will look into recent explanations of this puzzling phenomenon, discuss related insights, and challenge the modern belief that scaling up neural networks is always the best way to move forward.
Are the simplest models always the best choice? And is counting parameters really the best way to measure model complexity? Please join the seminar if you enjoy thinking about this kind of questions.

Course organization:
-Kick-off meeting at 16:00 on Monday, April 24th, 2022 (if feasible).
-We will have a block course in the break (date and time tbd at the kick-off meeting) with one presentation and discussion of a topic per person.
-Note that some (light load of) written deliverables will be due before the block course meeting and a seminar paper a few weeks after the meeting.

More information can be found here:

Requirements: The course has no formal requirements but preference will be given to Master students in Computer Science and related fields with prior knowledge in deep learning and a convincing description of their motivation.

Places: 12

Formal Compiler Security by Xaver Fabian, Mathis Kruse, Faezeh Nasrabadi, Robert Künnemann, Cas Cremers

Compilers are used to compile source languages (i.e. Rust) to target languages (i.e. Assembly). However, how can we be sure that security properties of the source code like Memory Safety or Constant Time are *preserved* by the compiler?
One way to achieve this is by defining correctness criteria that specify when a compiler is secure.

In this seminar, we will explore different kinds of correctness criteria for compilers and what security guarantees they offer. Furthermore, the course will discuss specific instances of secure compilers and which mechanisms they exploit (i.e. types, hardware features like enclaves) to attain security.

During the seminar, participants will learn how to differentiate between correctness criteria, the kind of security they achieve and what their limitations are.

Course Organization:
- The seminar will be run as a block course at the end of the lecture period during the break
- In order to enable participants to understand the material fully and better, the course will combine paper reading (at home), round table discussions with student presentations (in class), as well as lectures (in class).

More information can be found here:

Requirements: A basic understanding of programming (Programmierung 1, Programmierung 2) and compilers is required.

Having an interest in formal methods / semantics is a plus.
The language of the seminar is English.

Places: 12

Formal Methods for AI Safety by Rayna Dimitrova

The rapid progress in artificial intelligence and machine learning has lead to the deployment of AI-based systems in a number of areas of modern life, such as manufacturing, transportation, and healthcare. However, serious concerns about the safety and trustworthiness of such systems still remain, due to the lack of assurance regarding their behavior. To address this problem, significant efforts in the area of formal methods in recent years have been dedicated to the development of rigorous techniques for the design of safe AI-based systems.

In this seminar, we will read and discuss research papers that present the latest results in this area. We will cover a range of topics, including the formal specification and verification of correctness properties of AI components of autonomous systems, and the design of reinforcement learning agents that respect safety constraints.

We will meet (almost) weekly, in person.
Each participant will give a presentation of an assigned paper, followed by a group discussion. All students are expected to read each paper carefully and to actively participate in the discussions. To facilitate the discussions, each participant is required to submit two questions to the presenter of each presented paper in advance of the presentation. Each student will write a seminar paper on the topic assigned to them.

For more details, see the seminar website:

Requirements: There are no formal prerequisites for this seminar. However, participants are expected to have strong interest in formal verification and/or machine learning, and knowledge in these areas would definitely be helpful.

Places: 12

Getting Hands-On with Wearable Robotics for Augmenting Human Capabilities by Marie Muehlhaus, Artin Saberpour, Ata Otaran, Jürgen Steimle

Body-worn robots hold great promise for assisting users in physical tasks and augmenting their perception in unique ways. It can be expected that a variety of wearable robotic devices will soon find their way to end-users and become a relevant new platform for interactive computing.

Pioneering work has shown various forms of body-worn robots. For instance, these include wearable robotic arms that extend the human body with a third arm, exoskeletons that assist human movement and enhance human strength, or robots that freely move along the human body to assist with everyday tasks. Usage contexts range from assisting the elderly or users with specific needs, supporting workers in professional contexts, all the way to applications for mass users in everyday life, such as carrying heavy bags, new opportunities for sports, or to improve the immersiveness of applications in Virtual Reality.

The goal of this seminar is to acquire basic practical skills in building a Wearable Robot for human use, using Do-it-Yourself methods and Digital Fabrication tools alongside Arduino microcontrollers.
- In groups of three, you will design and implement a working robot that can take form of a wearable robotic arm or an exoskeleton.
- You will have the opportunity to design your own creative application case that your robot will enable, for instance to support applications in Virtual and Augmented Reality, assistive interfaces, interfaces for sports, or other domains.
- The seminar will conclude with a hands-on demo showcase where student teams can present their robots.

Requirements: - For the registration, we require you to submit a brief motivation statement that elaborates on why you want to take this class and what relevant projects and courses you have taken before.
- As our topics involve hardware, you are required to have basic experience in hardware programming (e.g., Arduino) and simple electronics (at the level taught in the Interactive Systems lecture).
- It's advantageous but not strictly required to have passed Interactive Systems and/or HCI.
- This is a Master-level seminar, which can also be taken by Bachelor students from the 5th study semester and above.

Places: 18

Hardware Security by Ali Abbasi

Secure software needs a reliable and truthworthy hardware. As a result, a secure hardware is crucial to build secure system.
This seminar covers research papers addressing various topics in hardware security. This includes topics such as hardware trojans, hardware side-channel, security hardware extensions, external memory security, security of hardware-based secure envlaves, hardware testing and hardware watermarking and counterfeit detection. As part of the seminar you will present a research paper and write a survey paper on the topic assigned to you. This course is offered in the format of a block seminar, and there will be no weekly classes.
More information:

Requirements: This seminar aims primarily at master students in Computer Security/Embedded Systems. In-depth background in systems security, hardware security, and embedded systems is essential. Do not take this seminar unless you have a background on the mentioned topics.

Places: 8

Hot topics in long-read sequencing by Andre Holzer, Sven Rahmann

The field of long-read sequencing has undergone significant advances in recent years and has become increasingly important in genomic research.

This graduate seminar in Bioinformatics will delve into the latest developments of long-read sequencing, and teach students about the newest technologies, applications, and tools in the field. The seminar will cover a range of topics including the principles, challenges, and latest advancements centered around PacBio & Nanopore sequencing, alongside highlighting examples of adaptation in research and clinical settings.

Through guided literature research, scientific writing, comprehensive presentations and group discussions, participants will gain an in-depth understanding of the current state of the field. Moreover, the seminar will showcase how these methods are being used to tackle complex genomic issues, such as obtaining accurate genome assemblies, monitoring metagenomes, resolving structural variations, or characterising epigenetic modifications.

The seminar is designed for students in Bioinformatics with an interest in expanding their knowledge and expertise in the cutting-edge field of long-read sequencing and will be offered as a block seminar in the summer semester 2023.

Seminar webpage:

Start date: April, 2023, on-site (TBA)

Requirements: The seminar aims at master students in Bioinformatics who preferably have a B.Sc. degree in Life Sciences. Successful completion of the lectures "Algorithms for Sequence Analysis" or "Single Cell Bioinformatics" can be helpful and is recommended but not a pre-requisite. Good language skills are presumed as all communications will be in English.

Note: This seminar gives 7 CP. Thus, you should be willing to invest a corresponding amount of ~210 hours for the preparation of your seminar material during the lecture period.

Places: 15

How to Make Computers Social? by Patrick Gebhard, Dimitra Tsovaltzi, Fabrizio Nunnari, Mina Ameli, Chirag Bhuvaneshwara

Computers, mobile phones, and wearables are part of our daily lives. Its user interfaces are designed to interact with facts, e.g. health parameters, documents, … – which is sufficient for some applications. But what if a computer system would understand users like human do and adapt to the individual social situation in order to establish a social human-like interaction? Such concepts are highly relevant to social training systems, e.g. virtual job interview training and work-life-balance systems. This interdisciplinary seminar in Psychology and Artificial Intelligence investigates the question „How to make computers social?“. What is social? What concepts, theories help to define being social? How do humans socially communicate? How can this be transferred into a computer model? What is technically feasible? How can this be exploited for social training systems? Relevant concepts and theories will be presented, discussed, and transferred into computer models. Three prototypical interactive social computer applications will be created as proof of concept. Students of Psychology and Computer Science will work together designing, discussing, implementing, and creating an evaluation plan for each application.

Requirements: Psychology students should have knowledge in the areas of models of emotions, models of social interaction and requirements. A bachelor degree in Psychology seems appropriate.

Computer Science students should have knowledge in the areas of AI, HCI, and software design. A bachelor degree in Computer Science (or equal) seems appropriate.

The main language is German, English is possible. Why? The seminar is about emotions and values that have to be discussed between psychology and computer science students. Our recommendation is that the seminar language is in German. If students agree that English is used, they should be aware that this will demand for additional efforts (e.g., in-deep explanations).

During the seminar, progress is reported at a specific web page for each project so every seminar participant can get an overview on the activities.

Project slides and short progress reports are in English!

Places: 9

Hybrid Learning and Reasoning by Matthias Klusch, André Meyer-Vitali, Andreas Nonnengart

This seminar (HyLEAR) is concerned with selected hybrid intelligent systems that combine techniques from subsymbolic learning (deep learning within area of machine learning) with symbolic techniques for reasoning, planning or learning. Both types of AI techniques have their strengths and limitations. While deep learning systems have been quite successfully applied to, for example, pattern recognition, image interpretation, speech recognition and translation, they can be characterized as overly data hungry, susceptible to adversarial attacks, opaque (non-interpretable by humans), and not informed by general principles such as causality or commonsense and domain knowledge. The successes of symbolic reasoning techniques (“good old fashioned AI”) are in such applications as automated (human-understandable, traceable) planning, diagnosis, design tasks, and question answering by cognitive virtual assistants but are often quite limited by the need of expensive, explicit knowledge acquisition and modelling, inefficient logic-based reasoning, and instability in the presence of noisy data. There is a consensus in the AI community that symbiotic, profound integration or combination of machine learning and reasoning is essential for human-level AI in general.

In this seminar, we will take a closer look at selected techniques and systems for hybrid learning and reasoning or planning, and discuss their strengths and weaknesses. The seminar type is classic in the sense that registered participants will present assigned topics, and discuss the strength and weaknesses of presented approaches. In addition, there will be two dedicated opponents for each presentation of an assigned topic.

Seminar webpage:

Seminar date and location: Wednesdays 10:15 - 12:00 CEST, on-site (DFKI, Bldg D3.2, Room "Turing 1") or virtually via zoom

NOTE: First session (Introduction with topic assignment) takes place on Tuesday 18.4.2023, 16:15 - 18:00 CEST

Requirements: This seminar aims primarily at advanced master students in Computer Science or Data Science and AI who preferably hold a B.Sc. degree in this or related field. Good knowledge in AI (introductory course on AI covering symbolic knowledge representation and reasoning, machine or deep learning, automated planning) is required.

Places: 9

Hyperproperties by Bernd Finkbeiner, Raven Beutner, Julian Siber

Traditional specification languages for systems usually refer to single execution traces and are therefore insufficient in many security-critical applications. This is because attackers may use comparisons between several different system traces to infer hidden secrets. Hyperproperties address this problem: Instead of specifying permitted behavior on single traces, they do so for sets of traces. The importance of research on hyperproperty specification and verification methods has recently been demonstrated by high-profile attacks such as Spectre and Meltdown, which exploit systems that violate certain information-flow policies. Further details on these attacks and their relation to hyperproperties can be found in this blog post:

In this seminar, we will have a look at state-of-the-art research on hyperproperties. This ranges from research on logics that describe hyperproperties, over verification algorithms, which check whether a system satisfies a property, to practical applications such as (runtime) monitoring.

The seminar will start with a group phase where students will present basic concepts in informal presentations. Subsequently, students will give individual talks on a research paper and hand in a summary at the end of the semester.

Seminar website:

Requirements: This seminar is open to Bachelor or Master students. There are no formal requirements to take this seminar. You should have an interest in logic and related topics (as discussed in lectures like “Verification,” “Semantics,” “Automata, Games and Verification,” or “Automated Reasoning,” although none of these lectures is a prerequisite). The seminar will take place in person.

The seminar takes place on Tuesdays, 14:15-16:00. The kick-off meeting is on April 18.

Places: 12

Machine Learning for Language and Vision by Xudong Hong, Ruitao Feng, Prof. Vera Demberg

Machine learning in language and vision has the potential to revolutionize the way we interact with computers, enabling more natural and intuitive communication, and bridging the gap between humans and machines. As we push the boundaries of these interdisciplinary domains, the development of sophisticated algorithms and models can lead to groundbreaking applications, such as creating more engaging storytelling, improving human-computer interfaces, and enhancing artificial intelligence's overall capability to comprehend and generate complex, context-rich information. By delving into state-of-the-art techniques, including pre-training, multitask learning, parameter efficiency, and reinforcement learning, we aim to inspire participants to further explore the exciting possibilities that lie at the intersection of language and vision.


Requirements: Students should have a basic understanding of deep learning, natural language processing and computer vision.

Places: 10

Machine Learning Security by Lea Schönherr

The intersection between security and machine learning can be viewed from two perspectives: The security of machine learning algorithms and systems, e.g., adversarial examples and poisoning attacks. Second is the use machine learning methods to improve and analyze the security of a system, e.g., malware detection or decompilation. In this seminar, we will cover recent publications from both sides by reading and summarizing the state-of-the-art on these two topics and performing an artefact evaluation of their code to verify and comprehend the practical implementations of the latest scientific publications.

The seminar is structured into two parts. In both parts, you will work in groups of two:

- you will write a short survey paper on the main topic of your assigned paper.
- you will evaluate the code of the paper during an artefact evaluation.

Additional information can be found at

Requirements: This seminar aims primarily at master students in Computer Science or related fields. Previous experience in machine learning and computer security is beneficial.

Places: 12

Opportunities and Risks of Large Language Models and Foundation Models by Prof. Dr. Mario Fritz

The advent of Large Language Models (e.g. ChatGPT, Github CoPilot) and other foundation models (e.g. stable diffusion,CLIP) has and will continue to change the way AI/ML applications are developed and deployed. E.g. the behavior and functionality of Large Language Models can be changed entirely by prompting the model, which can be understood as re-programming in plain English.

On the one hand, these models show unprecedented performance and can often be adapted to new tasks with little effort. In particular, large language models like ChatGPT have the potential to change the way we implement and deploy functionality.

On the other hand, these models raise several questions related to safety, security, and general aspects of trustworthiness, that urgently need to be addressed to comply with our high expectations for future AI systems.

Therefore, this seminar will investigate aspects of trustworthiness, security, safety, privacy, robustness, and intellectual property.

This is a lecture in the context of the ELSA - European Lighthouse on Secure and Safe AI:

Course URL:

Requirements: Solid understanding of machine learning and deep learning.

Places: 12

Photorealistic 3D Reconstruction with Deep Learning by Prof. Eddy Ilg

Computer vision has led to many recent technology break-throughs and is one of the most demanded fields. Even more, 3D computer vision is becoming increasingly important and the field has recently shown remarkable progress.

In this seminar, we will look at one of the most important aspects of understanding the 3D world: joint reconstruction of geometry and materials. While recent approaches based on NeRF, NeuS and DeepSDF have shown remarkable progess in reconstructing the geometry, material reconstruction is today still largely neglected. We expect that reconstructing materials will be key to the next generation of 3D computer vision algorithms.

The seminar will bring you up to speed with the concepts and state-of-the-art literature. After few introductory lectures, the seminar will continue with presentations to review the most important and most recent papers in the field. Overall, the seminar will set you up to be familiar with distinguished literature and enable you to start research in the field.

Every student is expected to give a 30min presentation, followed by a 15min discussion and hand in a write-up at the end of the seminar. Apart from the technical content, we offer mentoring on how to hold compelling presentations. This provides you the opportunity to learn key skills for job applications and your later career.

The seminar is offered by the Computer Vision and Perception Lab ( that focuses on building the next generation machine perception algorithms. The lab is offering Master's thesis, Hiwis and PhD positions. Please contact if you are interested.

Requirements: A background in deep learning and computer vision is required. A background in computer graphics is helpful.

Places: 12

Privacy Engineering und Recht by Prof. Dr. Sorge

Studierende erhalten während der Vorbesprechung ein Thema und müssen eine Seminararbeit hierzu anfertigen. Vor der Abgabe der fertigen Seminararbeit ist die Einreichung eines Abstracts vorgeschrieben. Nach der Abgabe des Abstracts kann bei Bedarf bei den Betreuern Feedback zu diesem eingeholt werden. Danach ist die Abgabe eines „Preprints“ der Seminararbeit erforderlich. Dies ist ein Vorabgabe der finalen Seminararbeit. Daraufhin findet eine Review der abgegebenen Preprints durch die weiteren Teilnehmer des Seminars statt. Jedem Studierenden werden hierfür 3-4 Paper anderer Studierender zugeteilt, welche von Ihnen reviewed werden. Die Review jedes Papers muss sich inhaltlich auf das gesamte Paper erstrecken und mindestens 400 Zeichen (für jedes Paper) enthalten. Studierende erhalten somit schon vor der endgültigen Abgabe der Seminararbeit Feedback von den anderen Teilnehmern des Seminars. Nach den Reviews finden die Vorträge statt. Abschließend werden die fertigen Seminararbeiten abgegeben.
Die Gesamtnote ergibt sich aus dem Preprint, den verfassten Reviews zu den Papern der anderen Studierenden, dem Vortrag und der finalen Seminararbeit.
Die Nichtabgabe des Abstracts, des Preprints, der Reviews oder der finalen Seminararbeit sowie ein Nichterscheinen zum Vortragstermin führt zum Nichtbestehen des Seminars.

Vorbesprechung: Montag, 24.04.2023 / 18-19:30 Uhr (Achtung: Geänderte Angabe!)
Anmeldung zur Besprechung der Abstracts: 04.05.2023
Abgabe Abstracts: 14.05.2023
Abgabe Preprint: 11.06.2023
Abgabe Reviews: 25.06.2023
Vorträge: 17.07.2023 und 18.07.2023 (Anwesenheit an beiden Tagen wird vorausgesetzt)
Finale Abgabe der Seminararbeiten: 06.08.2023

Requirements: Es wird erwartet, dass Teilnehmer in der Lage sind, Vorträgen in deutscher Sprache zu folgen.

Places: 7

Probabilistic Diffusion: Theory and Applications by Karl Schrader, Kristina Schaefer, Prof. Joachim Weickert

Probabilistic diffusion models are a popular class of neural networks, most famous for their ability to generate realistic images from text descriptions. They are a point of fascination not only for reasearchers, but have become a society-wide phenomenon. This seminar will explore the principles behind probabilistic diffusion models and will span the whole range from stochastic equations, over Markov processes, to beautiful images. Through our list of topics, participants will learn about the mathematical foundations of those models, and which insights are needed to turn those theoretical results into practice. We will explore the differences between popular models, and how their training can be improved. Furthermore, we will lightly touch upon adjacent areas like probablistic diffusion for audio generation, or ideas to protect art from being adapted.

You can find more information about the seminar and the papers you might present at .

Papers will be assigned based on an maximum weighted matching algorithm which tries to optimise the cumulative happiness of all participants.

Requirements: The seminar is for advanced bachelor or master students in Visual Computing, Mathematics, or Computer Science. Basic mathematical knowledge (e.g. Mathematik für Informatiker I-III) and some knowledge in image processing and computer vision is required.

Note in particular that you might be required to present a paper that assumes some basics from stochastic differential equations or other nontrivial mathematical knowledge.

Places: 14

Query Optimization: Past to Present (Block seminar) by Jens Dittrch, Immanuel Haffner

In the Database Systems core lecture we taught you about query optimization. In particular, you learned to compute optimal join orders under some cost model using dynamic programming. In this seminar, we will take a much closer look at query optimization. We will learn that there are different optimization goals, and hence cost models, and that for some cost models the optimization problem is NP-hard. We will learn about an algebraic cost model Cout that is a generalization of cost models for which the optimization problem is actually NP-hard. We will discuss different algorithms to compute join orders, including various bottom-up and top-down dynamic programming algorithms. Taking the topology of the query graph into account, we will also be looking at specialized algorithms for computing optimal join orders for particular kinds of queries in polynomial time. Sometimes, computing an optimal solution is not possible within a given time budget or simply not required. Therefore, we will also discuss algorithms for computing suboptimal join orders. Finally, we take a look at a recent work that tackles join order optimization as a graph search problem.

see here for planned papers and schedule:

Requirements: To succeed in this seminar, you must have passed our core lecture Database Systems. The knowledge that you acquired in this lecture enables you to comprehend and professionally present your assigned paper(s).

Places: 12

Rapid Game Development: Erstellung eines Computerspiels in einem interdisziplinären Team by Dr. Pascal Lessel, Jun.-Prof. Dr. Jonas Nesselhauf, Prof. Dr. André Miede, Christopher Olbertz, Prof. Dr. Burkhard Detzler, Dr. Michael Schmitz, Felix Henne

Die Veranstaltung wird hochschulübergreifend angeboten (HTW, HBKsaar, UdS). In interdisziplinären Gruppen soll innerhalb der Veranstaltung ein erster spielbarer Spieleprototyp entstehen, der den Unique Selling Point des Spiels verdeutlicht und aufzeigt, dass erfolgreich interdisziplinär gearbeitet wurde. In einer Gruppe arbeiten Studierende der praktischen Informatiker (HTW), Studierende aus der Fakultät MI - Fachrichtung Informatik (UdS), Studierende der Medienkulturwissenschaften der Philosophischen Fakultät (UdS) und Media Art & Design Studierende (HBKsaar) zusammen, um ein Spielkonzept zu entwickeln und verschiedenen Facetten eines Spiels zu realisieren (hier: Programmierung, Storytelling, Audiovisuelle Darstellung). Neben ihrem Gaming-Fokus und der Möglichkeit, Erfahrungen in einem interdisziplinären Team sammeln zu können, zeichnet sich die Veranstaltung auch dadurch aus, dass parallel zur Konzept- und Prototypphase regelmäßig Vorträge Einblicke in relevante Games-Themen geben.

Für Studierende der Fakultät MI - Fachrichtung Informatik wird diese Veranstaltung als Seminar angeboten.

Vor der Präferenzvergabe, prüfen Sie bitte alle Details auf der Webseite:

Das Kickoff findet am 18.04. statt.

Wichtig: Wenn Sie durch den Constraint-Solver einen Platz in diesem Seminar zugewiesen bekommen, werden wir die Informationen des internen Registrierungsformulars (Link siehe Webseite), heranziehen um die Gruppen zusammenzustellen. Bitte geben Sie daher Ihre Daten dort bis spätestens 16.04 ein.

The seminar will be given in German. Students of other universities might only speak German - so if you want to attend, you should understand German (as the presentations will be given in German) and ideally speak German as well.

Places: 14

Reproducibility in Computer Security by Thorsten Holz

A scientific paper consists of a constellation of artifacts beyond the document itself: software, hardware, evaluation data and documentation, raw survey results, mechanized proofs, models, test suites, benchmarks, etc. In some cases, the quality of these artifacts is as important as that of the document itself. In this seminar, you will learn more about replicability and reproducibility of artifacts in computer security. The seminar is structured in two parts. On the one hand, you will write a survey paper on the main topic of your assigned paper. On the other hand, you will evaluate the code of the paper in the context of an artifact evaluation. The goal is to replicate or reproduce the results presented in recent computer security papers and learn more about the latest results published at prominent security venues.

You will work in groups of two students. Note that the artifact evaluation requires an experimental evaluation of a given scientific paper.

Additional information can be found at

Requirements: This seminar is intended for advanced bachelor or master students in computer science or related fields. Prior knowledge of computer security is beneficial.

Places: 12

Simulating Reality for Boosting AI: Application of 3D Synthetic Data in Object Detection by Prof. Dr. Antonio Krüger, Dr.-Ing. Mohammad Mehdi Moniri

Large quantities of labeled data are needed for deep learning concepts. In the recent research and trends, synthetic data has provided promising results to boost the learning procedure. In addition to reducing ethical concerns (e.g., privacy) and providing the possibility to acquire data that are difficult to be produced in the real world, synthetic data are easier to generate and pre-annotate. Currently there are several frameworks that provide the possibility to accelerate the training and accuracy of perception networks based on the synthetic data (for example: NVIDIA Omniverse Replicator, Unity Computer Vision, and Unreal GT). In this seminar students have the possibility to use any available framework to implement an object detection application based on 3D synthetic data. The 3D data will be provided to the students and students will have free choice for selecting an open source or commercial technology for building their prototype. The result of this hands-on project will be an object detection system in virtual reality using the same 3D objects that are used during the training phase. Students will be presenting their research and prototype findings in several stages of the seminar. These projects will be realized in groups of four participants (total of three groups).

Requirements: Hands-on skills, motivation to do research and build prototypes. Previous background in machine and deep learning as well as computer vision is beneficial but not required if you are committed to learn the relevant fundamentals.

Places: 12

Software Engineering Research in the Neuroage by Sven Apel, Annabelle Bergum, Thomas Bock, Sebastian Boehm, Christian Hechtl, Christian Kaltenecker, Lina Lampel, Norman Peitek, Florian Sattler, Kallistos Weis

The pivotal role of software in our modern world imposes strong requirements on quality, correctness, and reliability of software systems. The ability to understand program code plays a key role for programmers to fulfill these requirements. Despite significant progress, research on program comprehension has had a fundamental limitation: program comprehension is a cognitive process that cannot be directly observed, which leaves considerable room for (mis)interpretation, uncertainty, and confounding factors. Thus, central questions such as “What makes a good programmer?” and “How should we program?” are surprisingly difficult to answer based on the state of the art.
Recently, researchers began to lift research on program comprehension to a new level. The key idea is to leverage recent methods from cognitive neuroscience to obtain insights into the cognitive processes involved in program comprehension. Opening the “black box” of human cognition will lead to a breakthrough in understanding the why and how of program comprehension and to a completely new perspective and methodology of measuring program comprehension, with direct implications for programming methodology, language design, and education.
In this seminar, we will review and discuss the past, current, and future developments in this area.

In this seminar, each participant has to perform a literature search and propose an experiment for the given topic.
Subsequently, the topic, the results of the literature search, and the proposed experiment have to be incorporated into a presentation and a written thesis.
To aid the literature search, the experiment proposal, and the presentation, this seminar includes multiple preparatory sessions at the beginning of the semester.
The student presentations will be held in June and July 2023.
All sessions will take place on-site at the university on Thursdays 12:15 PM - 2:00 PM.
Participation to all sessions is mandatory.

The topic assignment will take place on Thursday April 20, at 12:15 PM. Further information will be provided via e-mail after registration.

Requirements: Basic knowledge on software engineering and programming.

Places: 9

Specification-Based Testing and Debugging by Dominic Steinhöfel + Andreas Zeller

How can one specify inputs and outputs for a program and use these to test and debug it thoroughly? In this advanced seminar, we study several seminal approaches to automated testing and debugging and implement them all in a few lines using the all-new declarative ISLa test generator ( Our set of techniques includes:

* Grammar-based Testing
* Testing with Constraints
* Evolutionary Testing
* Property Testing
* Metamorphic Testing
* Explaining Failures
* and more!

The general process will be as follows: Each week, you get 1-2 _reading assignments_ and write an _abstract_ about them. We may also ask you to give an (ungraded) _five-minute short presentation_ to kick off the discussion and improve your presentation skills. Having discussed the approach, you have another week to finish a _programming assignment_ (using Python and Jupyter Notebooks). in which you implement the respective technique using the expressive ISLa framework (

At the end of the seminar, you give a 15-20 minute _presentation_ on one of the techniques, including experiments you designed and conducted. We will determine your final grade from your abstracts (10%), your programming assignments (30%), and the final presentation (60%).

For details, see:

Requirements: This seminar requires creativity and ambition. Experience with declarative languages and symbolic reasoning is a plus. Prior knowledge in automated testing, debugging, and software engineering (esp. from earlier courses) will be beneficial. In your motivation, please mention relevant projects and courses you have taken along with your grades.

Places: 10

SupRTwin: Sensing, Unterstanding, and Provisioning of Real-Time Digital Twins by Daniel Porta, Tim Schwartz, Sönke Knoch, Andreas Luxenburger, Antonio Krüger

A digital twin is a digital representation of a tangible or intangible asset from the real world in the digital world. In particular, they play a central role in the Industrie 4.0 as a means for digitalization.

Last year's iteration of the seminar focused on digital twins for automated production resources like robots. This semester, the seminar will focus on digital twins for human workers. 

In this practical seminar you will learn about relevant concepts of Industrie 4.0 and implement a certain aspect of a real-time digital twin of a human worker in a production environment. In small teams consisting of 2 - 4 students, you will be able to work with different (ambient and body-worn) sensoric systems and (no/low-code) AI frameworks for sensing and understanding the human workers actions and intentions. We will provide a list of possible ideas, but you can also propose your own ideas. 

This seminar will partially take place in the Power4Production Center at ZeMA (Eschberger Weg 46, 66121 Saarbrücken) in DFKI's Human-Robot-Collaboration Lab.

Requirements: To participate you should have
- basic knowledge in AI (e.g. in the field of computer vision)
- good programming skills in Python or C++
- some experience in ML frameworks like TensorFlow
- beneficial: experience in no/low-code AI frameworks like Google MediaPipe or Unity 3D

Places: 10

The Web Security Seminar by Giancarlo Pellegrino

In this seminar, students will learn to present, analyze, discuss, and summarize papers in different areas of Web security. The seminar is taught as a combination of a reading group with (almost) weekly meetings and a regular seminar, where you have to write a seminar paper. Specifically, each student will get a single topic assigned to them, consisting of two papers (a lead and follow-up paper).

For the weekly meetings, all students must read the lead paper, write a paper summary with strengths and weaknesses before the meeting. In the meeting, the assigned student will present the follow-up paper (20 minute presentation + 10 minute Q/A). Afterward, the entire group will discuss both papers.

Moreover, each student will write a seminar paper on the topic assigned to them, for which the two papers on the topic serve as the starting point.

The seminar slot is fixed on Wedn 14:00-16:00.

For more details and the timeline, see:

Places: 7

Through the eyes of the user: Seminar on eye tracking for intelligent interfaces by Anna Maria Feit

Looking into someone's eyes can tell you a lot about their state of mind, their intentions or their next actions; whether they are daydreaming or concentrating, whether they understand the math teacher's explanations or whether they are going to eat that last cookie. Using eye tracking, we try to bring that kind of understanding about a user's mind to a computing device, to enable a smoother, more efficient or more enjoyable interaction, be it on web pages, for gaming or with augmented reality interfaces.

This seminar will introduce students to the area of eye tracking research in particular with a focus on intelligent user interfaces. We will see how a person's gaze can be tracked, how we can infer their intentions and interests, their cognitive load, their language understanding, or expertise, and how such information can be used to improve our interaction with computers.

Students can take this course as either a seminar or a proseminar. As such, it brings together Master and Bachelorstudents. It is highly interactive and builds on the active participation of all students throughout the semester. Every week students will read papers from eye tracking and human-computer interaction and prepare a set of discussion questions. In addition, participants take turn in assuming different roles, such as presenter, teacher, journalist, etc. looking at the material from different viewpoints.

See here for more details:

Regular meeting slots are on Thursdays 14:15 - 16:00

Places: 9

Topics in Adversarial Machine Learning by Xiao Zhang

This seminar will focus on understanding the security threats adversaries pose to machine learning systems and the recent algorithmic advancements in building more robust machine learning systems to mitigate those threats. In addition, we will look into several theoretical works on understanding and characterizing the fundamental limits of adversarial machine learning.

Each week, a team of students will lead discussions on a topic in adversarial machine learning assigned in advance (including a 45-min presentation plus a 30-min Q&A session). After each presentation, the team will also write a blog summary. Other students must read a few assigned papers on the topic in advance, write a review for one of these papers, and prepare three well-thought questions.

Moreover, students must contribute fully to a team that develops a course-long project and write a seminar paper on their assigned topic.

For more details and the timeline, see:

Requirements: Previous background in mathematics, statistics, machine learning, and security would be beneficial but not required as long as you are motivated and able to learn relevant fundamentals. Students in the seminar should have either a strong machine learning background or a strong security background, but you are not expected to have an extensive experience in both areas. The seminar is open to ambitious undergraduate students (with permission of the instructor) and graduate students interested in adversarial machine learning research and other related topics in trustworthy machine learning.

Places: 10

Trusted and Secure Computing by Sven Bugiel, Michael Schwarz, Dhiman Chakraborty

In this seminar, the participants will discuss and evaluate state-of-the-art research solutions in the domain of secure, trusted, and trustworthy computing, both from the constructive as well as from the offensive perspective. The focus is particularly on hardware-based security architectures that are becoming omnipresent in different settings like server, cloud, or embedded device security. Examples of such hardware security primitives are Trusted Platform Modules, Intel SGX, RISC-V Keystone, or ARM TrustZone.

Course in the CISPA CMS:

Requirements: There are no formal prerequisites beyond a basic knowledge of how computer systems work internally. Some of the seminar papers will talk about a certain hardware configuration. But no formal background in hardware design is required. Previous participation in “Side-Channel Attacks and Defences” by Dr. Michael Schwarz can be helpful in understanding the topics easily.

Places: 8

What do language models really understand? by Sebastian Schuster, Vera Demberg

Large language models such as GPT-3 and ChatGPT have led to great advances in the field of natural language processing, and in many cases they provide responses to prompts that suggest that possess non-trivial abilities to understand language. At the same time, however, these models are primarily trained on text and have no explicit connection with the real world, whereas humans learn language by interacting with other humans and forming associations between words and phrases and entities and events in the world.

In this seminar, we will focus on the question to what extent large language models understand language. We’ll cover different philosophical schools of what it means to understand language, and then focus on a series of recent empirical papers that aim to evaluate different aspects of language understanding in models.

Course website:

Requirements: Students should be familiar with deep learning and the transformer architecture.

Places: 6

Wireless Security by Mridula Singh

We are surrounded by wireless systems to share confidential information, access bank accounts, report heart rate, etc., incentivizing attackers to eavesdrop and manipulate wireless communication. In this seminar, we will discuss the security, privacy, and availability aspect of wireless systems we use today. During the first half of the semester, each student will read 4-5 research papers. In the second half, students will work on projects in a team of 2-3 students. We will meet weekly to discuss the papers and progress of projects. Finally, students will give a 25 min presentation at the end of the semester.

Seminar website -

Requirements: There is no formal course requirement for this seminar. Knowledge of signal processing and embedded systems would be useful.

Places: 8