Seminar Assignment Winter 2025
The central registration for all computer science seminars will open on Sep 5th.
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 Oct 14th, 23:59 CET. You can select which seminar you would like to take, and will then be automatically assigned to one of them on Oct 17th.
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, please do not 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"). The system will then prioritize you for assigning 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 performed by a constraint solver on Oct 16th, 2025. 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.
Seminars
Advances in Hybrid Artificial Intelligence by Matthias Klusch, André Meyer-Vitali, Andreas Nonnengart, André Antakli
This seminar (HAI) is concerned with selected advances in hybrid AI with focus on neuro-symbolic learning and planning methods. Hybrid AI research investigates the feasability and benefit of combining different methods from one or different subfields of AI such as machine learning including deep learning, AI planning, automated reasoning, vision, and multi-agent systems. One prominent form of hybrid AI is neuro-symbolic AI that strategically integrates the strengths of symbolic reasoning and planning with the pattern recognition and learning capabilities of neural networks. It aims to overcome the inherent limitations of traditional symbolic systems, such as brittleness and the knowledge acquisition bottleneck, and purely connectionist deep learning models, which often suffer from opacity ("black box" problem), data hunger, and a lack of common sense or logic-based reasoning. We will take a closer look at selected methods and systems for neuro-symbolic learning and AI planning, including LLM-assisted approaches, and discuss their strengths and weaknesses.
The seminar type is classic in the sense that registered participants will present assigned topics. In addition, there will be two dedicated opponents for each presentation of an assigned topic.
Seminar webpage:
https://www.dfki.de/~klusch/HAI-seminar-ws25/
Requirements: This seminar aims primarily at advanced bachelor and master students in Computer Science and DSAI. Solid knowledge in AI (ideally, taken and passed introductory courses on AI, planning, ML, genAI, or sufficient knowledge on these areas from other sources) is required.
For more information, please check the seminar webpage.
Places: 10
AI Safety by Yang Zhang
As AI systems become increasingly powerful and integrated into critical aspects of society, ensuring they behave safely and reliably has never been more important. AI Safety is the interdisciplinary field focused on minimizing risks associated with AI, from algorithmic bias and system failures to the long-term challenges posed by advanced autonomous agents.
In this seminar, we will explore the key technical, ethical, and societal issues related to AI safety. Topics include value alignment, robustness, and the governance of powerful AI systems. By the end of the seminar, students will gain a foundational understanding of how to assess and mitigate risks, design safer AI systems, and contribute to responsible AI development.
Requirements: Students are required to have a basic understanding about data analysis and machine learning.
Places: 12
Aspects of Quantitative Program Verification by Benjamin Kaminski, Tobias Gürtler, Anran Wang
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: 6
Building an Operating System from Scratch by Antoine Kaufmann
In this course all participants will jointly build an operating system from scratch. You will learn how modern computers and operating systems actually work, including all the nitty-gritty details. More generally you will gain experience for what working on low-level software is like, and how to
More information here: https://cms.sic.saarland/buildos_25/
Requirements: Critically, since this is a major joint venture project, you have to be able to contribute throughout the semester. This is not a course where you can put off work to the end of the semester when there is a deadline. Others depend on you to complete your pieces.
This seminar is open to senior Bachelor, Masters, and doctoral students. Ideally, students should have already taken courses on system architecture and operating systems, or at the very least be ready to quickly & independently read up on the necessary bits. Bachelor students must have passed the basic courses on Programming 2 or equivalent. Proficiency in C/C++ programming (including low-level aspects such as pointers and memory management) and UNIX development tools (e.g., shell, make, gcc, gdb) is strictly required to succeed in this course.
The language of the seminar is English. All meetings and communication with the course staff will be conducted exclusively in English.
Places: 15
Complexity of Games by Daniel Marx
Popular games hide computationally hard, sometimes even undecidable, algorithmic questions such as whether a player has a winning strategy – and some argue that this makes these games popular in the first place. In this seminar, we study (generalizations) of popular games, such as board, card and video games, for example: Hanabi, Chess, Minesweeper and Portal. They might be zero, one or multi-player games, and interesting problems to study range from whether there is a forced win, to simply whether there is a legal move. These problems often lead us to complexity classes beyond NP such as to PSPACE.
Seminar is on Tuesdays at 16:00.
Webpage: https://cms.cispa.saarland/compgames_2526
Requirements: A solid background in algorithms and complexity. You should be familiar with NP and reductions to show hardness.
Places: 10
Current Research in Databases by Jens Dittrich
This seminar builds upon our courses "Big Data Engineering" and "Database Systems". We will discuss recent research papers from SIGMOD and PVLDB. Students are expected to present one paper each and give read and give feedback to two other papers. The presentations will happen at the end of the semester. Though this seminar is meant to be one of the few seminars at the department not treating AI, we cannot fully guarantee that we might incidentally touch AI topics.
Requirements: Prog 2, BDE, if possible: Database Systems (but not mandatory)
Places: 12
Data and Society by Prof. Ingmar Weber, Dr. Annika Haß, Dr. Till Koebe
From finding a mate, to booking a holiday, our lives are increasingly mediated by online platforms. Digital traces left by these interactions provide opportunities to study societal phenomena while creating challenges around the responsible use of data. In this seminar, students will learn how computational methods and machine learning can be applied to study society through such data.
The first part of the seminar will familiarize students with existing work in computational social science. Each week, we will focus on a different topic such as “Digital Democracy” or “Gender Gaps” and explore methods to quantify these phenomena. The second part of the seminar will be about projects in which students are asked to quantify a societal phenomenon of their choice using computational methods. Here, students can both propose topics or choose from topics defined by the lecturers.
The overall course performance will be based on (i) overall course participation, (ii) assigned paper presentations, (iii) a project pitch and (iv) the written project report.
Apart from learning about interdisciplinary research and applications of machine learning, students will also learn research skills such as how to read and discuss papers, how to plan a project, how to present their work, how to write a scientific paper, and how to work in teams.
Students can take this course as a seminar.
Future details at https://cms.sic.saarland/das_2425/. Timing is Fridays, 10am-12am.
Requirements: Msc students only – the project-based element of the seminar will require some Python programming and data analysis experience.
An interest beyond the foundations of CS, and caring about societal problems is a must.
Places: 12
Deep Learning Efficiency: Smarter AI, Not Just Bigger by Rebekka Burkholz
Deep learning is behind many of today’s most exciting AI breakthroughs — from ChatGPT and self-driving cars to drug discovery and image generation. But there's a catch: these advances often come with massive computational and memory costs, putting them out of reach for all but the biggest tech companies.
How can we make cutting-edge AI more efficient, accessible, and sustainable?
In this seminar, we’ll explore recent strategies that aim to make deep learning smarter, not just bigger. We’ll read and discuss cutting-edge research papers that tackle key questions like: Can smaller models perform just as well as massive ones? How can we train and run AI systems using less data, time, and compute? What are "lottery tickets" in neural networks — and why do they matter?
You’ll gain insights into theoretical foundations, practical techniques, and current challenges in building efficient AI systems. Whether you're interested in ML research, want to build powerful models on a budget, or are just curious about the future of AI beyond scale — this seminar is for you.
More information can be found here:
https://cms.cispa.saarland/dle25/
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 motivation.
Places: 14
Deep Probabilistic Generative Models by Maria Martínez & Isabel Valera
With the development of neural networks and increased computational power, deep generative modeling has emerged as one of the leading directions in AI. We are shifting from traditional discriminative tasks (such as classification, segmentation, or clustering), which focus on modeling conditional distributions, to a more comprehensive framework aimed at modeling the joint distribution of the data itself. Discriminative models alone can be insufficient for robust decision-making and the development of intelligent systems, as it is also necessary to understand the underlying data-generating process and be able to express uncertainty about the environment.
Typically, in deep learning literature, generative models are viewed as methods for synthesizing new data. However, in this seminar, we will adopt a probabilistic perspective to highlight that modeling the marginal likelihood of the data has much broader applicability, and this could be essential for building successful AI systems.
In this seminar, we will ask ourselves how to formulate deep generative models (i.e., how to express and learn the marginal likelihood of the data) and explore the different approaches proposed in the literature. The aim is for students to critically assess existing methods, understand their strengths and limitations, and identify potential directions for future research.
Requirements: Pre-requisites: This seminar aims primarily at master students in Computer Science, DSAI or related fields, who have prior knowledge of machine learning. Participants should have already taken one or several courses related to machine learning, e.g., core machine learning, elements of machine learning, linear algebra, neural networks, etc.
Evaluation based on a presentation, participation in panel discussions and a final report.
Places: 12
Differential Privacy in the Era of Foundation Models by Franziska Boenisch
In recent years, foundation models, such as GPT, LLaMA, Dall-E, or Stable Diffusion, have transformed the field of machine learning, particularly in large-scale tasks like natural language processing and computer vision. These models, trained on vast datasets, are capable of transferring their learned knowledge to a wide range of applications, making them incredibly powerful and versatile. However, this also raises significant privacy concerns when sensitive data is involved.
This seminar will explore how differential privacy (DP), the leading standard for privacy protection, can be applied to foundation models to mitigate these risks. DP ensures that changes in individual data points in a model’s training data minimally affect the overall model predictions, providing a safeguard for privacy even in the most data-intensive models. We will dive into the fundamentals of both DP and foundation models, study how they intersect, and explore strategies for integrating privacy guarantees into these cutting-edge systems. Key topics will include the theory behind DP, practical privacy-preserving mechanisms, and case studies of DP implementation in advanced foundation models.
Requirements: This seminar is open to senior Bachelor, Masters, and doctoral students. Ideally, students should have a solid background in mathematics and machine learning through the base lectures, and a strong interest in deep learning.
Each student will present a topic during the seminar hours in the form of an oral presentation. In addition, each student will read the relevant papers for the other students’ presentations, and hand in a seminar paper at the end of the semester.
Places: 20
Explainable Machine Learning Seminar (ExML) by Jonas Fischer, Bernt Schiele
In this seminar we will discuss different methodologies in Explainable Machine Learning, which is concerned with understanding what information a Machine Learning system learns and how it uses this information for decision making. We cover both seminal works as well as recent advancements in the field, including post-hoc explainability approaches and inherently interpretable model designs.
The seminar will consistent of an introductory meeting with a lecture at the beginning of the semester introducing the field and distributing papers, and a two-day block course in the semester break covering paper presentations and discussions. Students are expected to read into their assigned paper, the related literature, prepare a talk, as well as a paper summary with critical discussion, and conduct a small practical project around their topic.
Requirements: The student has a solid understanding of Machine Learning and feels comfortable with Neural Networks (for example through lectures High Level Computer Vision, Neural Networks: Theory and Implementation, or Machine Learning).
Places: 12
Explainable Reinforcement Learning on GPUs by Julian Groß, Gian-Luca Kiefer, Prof. Antonio Krüger
In this seminar, you will learn the basics of GPU programming and its application to reinforcement learning, specifically Deep Q‑Learning. You will also become familiar with explainability in neural networks, which is crucial for understanding and interpreting decisions made by AI systems. You will be assigned a scientific paper to present, covering one of the topics listed below (GPU programming, reinforcement learning, or explainability). In addition to the presentations, you will work on a practical project to implement and apply the concepts you've learned. The project culminates in a final presentation in which you showcase your work and findings, with a specific focus on your assigned topic.
You can find additional information on the seminar website:
https://umtl.cs.uni-saarland.de/teaching/winter-2025/2026/explainable-reinforcement-learning-on-gpus.html
Requirements: You should have passed Programming II, the Software Praktikum, Concurrent Programming (Nebenläufige Programmierung), and Mathematics for Computer Scientists I–II (or Analysis I and Linear Algebra I). Passing the Software Engineering core lecture and a course on Machine Learning or Neural Networks is a plus. You are expected to be fluent in a C‑like programming language.
Places: 10
Formalizing Mathematics in LEAN by Leon Pernak
L∃∀N ("lean") is a modern theorem prover and functional programming language that allows
mathematicians to write formal proofs with computer verification. It is increasingly used in
the mathematical community, where the applications range from verifying high-level research
mathematics like the Liquid Tensor Project to experimenting with how far AI can take us in
writing mathematical proofs.
The seminar will give a gentle introduction to the L∃∀N theorem prover, learning its syntax,
concepts, and how to use it to formalize your own proofs. Participants will spend the majority
of time working at their own speed on exercises that teach the language, adjusted to their
mathematical background. The goal (and graded coursework) will be the formalization of some
mathematics (or other type of theory) of each participant's choosing.
More Info on CMS: https://cms.sic.saarland/fml/
Requirements: Neither mathematical background nor programming experience is required to participate in the
seminar, and students new to both mathematics and computer science are very much encouraged
to participate, but more experienced students in either topic can also be sure to find challenges
at their level.
Places: 20
Generative AI for Education by Adish Singla
The course will provide an overview of state-of-the-art research on leveraging generative AI to enhance education. We will cover a broad set of research papers and topics inspired by the NeurIPS'23 workshop we organized (workshop link: https://gaied.org/neurips2023/). The course consists of three main components as follows:
(1) Research papers: During the first half of the semester, students will be assigned up to six 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 a project.
(3) Final presentation: At the end of the semester, students will give a presentation on one of the papers and the project.
The course will be similar to the seminar course we offered in the Summer Semester 2024 (course link: https://machineteaching.mpi-sws.org/course-gaied-s24.html). The set of research papers will be updated to cover more recent results. In the previous year, the course was taken by a diverse set of students, both from the Department of Educational Technology and from the Department of Computer Science.
There will be no weekly classes. We will schedule regular office hours where students can receive feedback on their reports or 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 human-computer interaction, educational technologies, natural language processing, artificial intelligence, software engineering, and program analysis.
(2) We are requesting you to provide a short motivation letter explaining the reasons why you are interested in taking this seminar. In this motivation letter, you can also mention any relevant project(s) you have done and any relevant courses you have taken. Please provide this information in the text box below.
Places: 10
Hands-On Computer Architecture by Sebastian Hack
Requirements: You have to have participated in the 2025 iteration of the building and 8-bit computer from scratch course.
Places: 2
Hot Topics in Data Networks by Anja Feldmann, Tobias Fiebig
While the Internet has started as a research effort, it has consistently evolved throughout the decades into the largest commercial network. Today, many research efforts focus on understanding the Internet's structural trends, optimizing its packet delivery, and laying the foundations for its future developments. In this seminar, you will receive a closer look at bleeding-edge research published at the top conferences in our domain. Discussing state-of-the-art approaches and recent findings from a broad range of network-related topics with your peers and instructors will provide you with a deep understanding of your assigned topic. Preparing the accompanying research survey and topic presentation will not only strengthen your academic reading and writing skills but also help you to present your future work in a more accessible and structured way.
Requirements: Participants should have successfully completed "Data Networks" or an equivalent course.
Places: 12
Just Beyond P by Danupon Nanongkai, Evangelos Kipouridis, Daniel Neuen, Karol Węgrzycki
In this seminar, we will explore algorithmic problems that lie at the edge of our current understanding—problems that admit surprisingly efficient algorithms (e.g., quasipolynomial-time) but for which no polynomial-time solution is known, and no strong hardness evidence rules one out. These are often natural candidates for inclusion in the class NP ∩ coNP or are solvable by randomized algorithms with no known deterministic counterparts.
We will discuss a variety of such problems, including:
- Graph and Tournament Isomorphism: classic problems in NP ∩ co-AM, recently shown to be solvable in quasipolynomial time.
- Energy Games and Infinite Duration Games: fundamental problems lying in NP ∩ coNP, but not known to be in P.
- Min-Sum of Radii Clustering: admits a QPTAS and quasi-polynomial exact algorithms under reasonable assumptions, yet no known PTAS.
- Makespan Scheduling with Precedence Constraints: a well-studied scheduling problem with subtle complexity, lacking strong evidence for hardness or tractability.
- Exact Matching: solvable in randomized parallel polylogarithmic time, but no deterministic polynomial-time algorithm is known, even for bipartite graphs. The problem opens the door to discussions on derandomization and complexity classes like BPP and E.
This seminar will be informal, discussion-driven, and problem-oriented. Each session will spotlight one or two problems, exploring known results, open questions, and why these problems resist classification. Participants are encouraged to bring their own favorite "mysterious" problems to the table.
Requirements: Each student will choose a research paper from a curated list provided by the organizers. Before presenting in class, students are required to give a practice talk to one of the instructors. The in-class presentation should clearly explain the problem addressed in the paper, outline the main techniques used, and discuss the significance of the results.
Places: 10
Legal Tech und eJustice by Christoph Sorge
Das Seminar „Legal Tech und eJustice” ist ein interdisziplinäres Seminar für Informatiker (im weiteren Sinne) und Juristen.
Ein Interesse an interdisziplinärer Zusammenarbeit ist erwünscht; einige der angebotenen Themen eignen sich besonders dafür, in interdisziplinären Teams bearbeitet zu werden. Für die Anrechnung als Informatikseminar sollte der Schwerpunkt in der Informatik liegen. Es sind auch rein technische Themen möglich, die lediglich Bezug zu juristischen Anwendungen haben.
Inhalte des Seminars:
Der Begriff "eJustice" bezeichnet die Digitalisierung im Justizwesen, mithin den Einsatz von IT-Verfahren bei Gericht und Anwaltschaft. Dies umfasst beispielsweise die elektronische Aktenführung, Online-Gerichtsverfahren und digitale Kommunikation zwischen Gerichten, Anwälten und Behörden, um gerichtliche Prozesse effizienter, transparenter und zugänglicher zu gestalten.
"Legal Tech" bezeichnet die Informationstechnik zur Unterstützung juristischer Arbeit, wie beispielsweise automatisierte Vertragsprüfung, KI-gestützte Rechtsberatung, digitale Tools zur Dokumentenerstellung.
Ablauf des Seminars:
Vorbesprechung: Einführung und Themenvergabe.
Abstracts und Preprints: Einreichung und Feedback-Runden.
Peer Reviews: Bewertung der Arbeiten durch andere Teilnehmer.
Vorträge: Präsentation der Seminararbeiten.
Abschlussarbeit: Finale Abgabe der ausgearbeiteten Themen
Requirements: Es wird erwartet, dass die Teilnehmer in der Lage sind, Vorträgen in deutscher Sprache zu folgen und Ausarbeitungen in deutscher Sprache im Rahmen des Peer Review zu lesen (eigene Vorträge und Ausarbeitungen können aber in deutscher oder englischer Sprache angefertigt werden).
Da Schwerpunkte des Seminars aus technischer Sicht in den Bereichen KI-Anwendungen und Security liegen, sind Vorkenntnisse in einem der Bereiche hilfreich.
Places: 7
Living "AI-ducation" Dashboard by Tomohiro Nagashima, Sarah Malone
The rise of artificial intelligence (AI) is transforming everyday lives, including education, and it requires us a deep understanding of and research insights into its applications and implications in the field. This seminar aims to equip students with the knowledge and skills needed to critically analyze AI in education and contribute to this evolving field. The seminar is jointly taught by Prof. Tomohiro Nagashima in the CS department (https://tomonag.org/) and Dr. Sarah Malone in the Education Science department (https://www.uni-saarland.de/lehrstuhl/bruenken/personen/dr-sarah-malone.html), and it targets students in both departments.
During the seminar, students will collaboratively design and develop a "Living AI-education Dashboard," a dynamic resource that summarizes and visualizes current research, trends, and data on AI in education. Through project-based learning, students will gain hands-on experience in data visualization, dashboard creation, dashboard design, and research methods (e.g., how to conduct systematic literature review and user-centered research). Students would also interact with education stakeholders to gain deep insights into what different stakeholders would wish to see on the dashboard, and incorporate their insights into the design. They will also develop interdisciplinary thinking by integrating concepts from both computer science and education science and through collaborations across the domains. The course is taught by an interdisciplinary team that encourages collaboration between departments and prepares students to tackle complex, real-world problems.
The seminar will be offered on Mondays 10-12:00 (location TBD).
Feel free to contact nagashima@cs.uni-saarland.de for any questions. Find out more about the seminar here: https://tomonag.org/aiducation/
*Note that you may not take the seminar this semester if you have taken the previous iterations of this seminar.
Requirements: It is highly recommended that students are familiar with data visualization and its tools (e.g., Tableau). However, it is not a strict requirement; please describe your experience with data vis in your application.
Places: 10
Machine Learning for Language Processing by Dietrich Klakow
Deep learning is the predominant machine learning paradigm in language processing. In this seminar we will focus on generic algorithms for language models as well as their application to a variety of languages and other string data eg from bioinformatics.
For more information and the specific list of topics see
Places: 8
Milestones in Machine Learning and Language: Historical Readings by Yash Sarrof
Modern AI feels like it’s everywhere — models that write, speak, see, play games, and even arguably reason. However many researchers today feel a sense of déjà vu: incremental papers, rebranded benchmarks, recycled ideas. Are we reaching the limits of what can be achieved just by scaling models? Is the field running out of new ideas? This seminar takes a step back — and way back — to understand how machine learning and language technology evolved: both technically as well as philosophically. We’ll examine the early hopes, dead ends, breakthroughs, and rediscoveries that brought us to today's transformer-based models. We'll ask:
- What did early AI researchers believe language and learning were?
- Why were neural networks once declared useless — and then revived to define modern AI?
- What kinds of research actually shifted paradigms?
- Are we at a similar inflection point today?
Requirements: Strong interest in reading Math and notation heavy papers.
Places: 12
N/A by Adam Dziedzic
N/A
Requirements: N/A
Privacy Systems and Applications Seminar by Wouter Lueks, Sylvain Chatel
As technology becomes prevalent, we carry more and more devices everywhere we go and our digital trail becomes more and more pronounced. On the one hand, digitalization brings enormous benefits. On the other hand, it makes it almost much easier to violate user's privacy, to surveil large fractions of a population, and sometimes even to control or influence what people do and think.
In this seminar, we will look at privacy-enhancing technologies, digital means that can help counteract this reduction in privacy caused by increasing digitalization.
We will read and discuss new and seminal papers to learn about new techniques and ideas in the field of privacy-enhancing technologies. You will learn how to critically analyze and present existing research papers, emulate a small scale conference, and think about your own research ideas.
Example of topics covered include: Systems for End-to-End Privacy, Anonymous Communication Systems, Private Set Intersection, Private Information Retrieval, Fully-Homomorphic Encryption, Censorship Resistance Systems.
Students will present, write reviews, and write a survey paper. See https://cms.cispa.saarland/psas25/ for a full overview.
Requirements: Basics of cryptography and security: required
Advanced cryptography and PETs: strongly recommended
Places: 10
Router Lab by Fariba Osali, Q Misell, Vaishnavi Raghavajosyula, Tobias Fiebig
In this seminar, we take a hands-on approach to explore the workings of internet components and provide a deep understanding of the underlying protocols. Specifically, we examine how routers and switches can be configured and connected to a working IP network.
The seminar consists of a series of activities starting with setting up the hardware and introducing basic configuration for VLANs and IPv4/IPv6 networks and gradually moving to more advanced topics, including but not limited to, routing protocols, virtual private networks, security, network monitoring, and troubleshooting.
Requirements: Participants should have sufficient knowledge of computer networks and how the Internet works, e.g., by successfully completing "Data Networks" (or an equivalent course), or by demonstrating relevant prior practical experience.
Places: 12
The Humans of Computing: Past, Present and Future by Mannat Kaur, Tobias Fiebig
Technology is not created in a vacuum. It is created, operated and used by people. As such, it cannot be fully understood without accounting for the role of humans. This seminar will explore system and network operations through a sociotechnical lens.
We will explore the question, “how did we get here and where are we going?”
In order to move forward, it is important to understand where we come from. We will begin by diving into the (recent) history of computing and the Internet. We will then examine current sociotechnical research into system and network operations. After this, we will collectively imagine our technological futures.
Particularly, the learning objectives of this seminar are:
• Understand the gendered history of computing
• Discover the role of certain key figures, both in the past and present
• Describe system and network operations as a sociotechnical system
• Discuss the role of gender in today’s computing infrastructure and operations
• Imagine equitable digital futures
Requirements: Participants should be interested in the historical and societal aspects of technology. Caring about social issues and social justice is a must.
Places: 15
Theoretical Abilities and Limitations of Language Models by Xinting Huang, Michael Hahn
LLM have amazing capabilities, but also hallucinate and make reasoning mistakes. Can we understand these abilities and limitations theoretically, as way to figure out ways of overcoming them? The incredible scale of current LLMs makes this a daunting prospect. However, recent research has developed mathematical understanding sheeding light on key questions, such as: why LLMs struggle with basic tasks like arithmetic, what kinds of problems transformers can and cannot solve without chain-of-thought, how they generalize, and what architectures might come next. Drawing on ideas from complexity theory, formal languages, and learning theory, the seminar is open to all with a willingness to engage deeply with technical content.
https://lacoco-lab.github.io/courses/theory-25/
Requirements: Good understanding of Machine Learning and Neural Networks. Good foundation in Math and Theoretical Computer Science
Places: 12
The Web Security Seminar by Giancarlo Pellegrino, Ben Stock
The Web Security Seminar will teach students to present, analyze, discuss, and summarize papers in different *advanced* topics of Web security. The seminar combines a reading group with (almost) weekly meetings and a regular seminar, where students will write a seminar paper.
Each student will get a topic assigned, consisting of a lead and a follow-up paper. The student will present the follow-up paper in a 20-minute presentation followed by a 10-minute Q&A. Afterwards we will all discuss the lead paper as a reading group. All students must read the lead paper and, before each session, must submit a summary with strengths and weaknesses.
Finally, each student will write a seminar paper on the assigned topic, for which the two papers serve as the starting point. Special attention should be paid at fulfilling the seminar paper's objective.
This seminar adopts a strict no LLMs/GenAI policy.
Link: https://cms.cispa.saarland/websecsem_sose25
Requirements: Students must be familiar with most important web security topics, e.g., SOP, vulnerabilities (e.g., XSS, CSRF, and SQLi), and defenses (e.g., validation, sanitization, CSP, etc).
Also, students must write a short motivation statement to explain their interest in Web security.
Places: 11
Topics in Optimization for Machine Learning by Sebastian Stich
Optimization is central to many machine learning algorithms. This seminar provides an overview of modern optimization methods for machine learning and data science, covering the theoretical foundations of stochastic optimization, the scalability of algorithms to large datasets, and challenges in distributed optimization, such as federated learning and privacy aspects. We will study a mix of foundational papers and recent research publications.
Organization:
- There is no weekly meeting. The presentations will be clustered into 2-4 slots (dates to be decided), roughly between the end of November and January.
- A kick-off meeting will be held virtually during the second week of the semester.
Note that - besides the block format - there are some written deliverables due during the semester, as well as a (mandatory) meeting with the tutor to get feedback on your report and presentation slides
Additional information can be found at https://cms.cispa.saarland/optml_seminar_2526/
Requirements: This seminar aims primarily at master's students in Computer Science or related fields. Previous experience in machine learning, data analysis, or optimization is beneficial.
Places: 10
Trusted AI Planning (TAIP) by Jörg Hoffmann
AI planning agents need to take action decisions towards a long-term objective. Learned action policies, in particular neural networks, that map environment states to actions are gaining ever more popular for this purpose. Yet such learned policies come without any inherent guarantees regarding desirable properties such as safety. The seminar covers recent research on quality assurance methods, including verification, testing, and re-training of learned action policies.
Requirements: Students must have passed the AI core course or the Trusted AI Planning specialized course.
Places: 16
Trustworthy Agentic Systems by Lea Schönherr
When AI systems move from pattern recognition to decision-making, they stop being just tools and start becoming agents. These agents can plan, act, and adapt, qualities that make them powerful but also raise questions about reliability, safety, and alignment with human goals.
This seminar investigates what it means to build trustworthy agentic systems. Instead of focusing on scale or efficiency, we’ll center on issues like:
How do we evaluate whether an AI system deserves trust?
What design principles can reduce the risks of unintended behavior?
How can humans and AI collaborate without losing oversight or control?
By the end of the seminar, you’ll have a deeper grasp of the challenges that lie ahead for autonomous AI and the frameworks researchers are developing to meet them.
More information can be found here:
https://cms.cispa.saarland/tas/
Requirements: The course has no formal requirements, but preference will be given to Master students in Cybersecruity and Computer Science and related fields with prior knowledge in deep learning and a convincing motivation.
Places: 12
Trustworthy Machine Learning by Adam Dziedzic, Andreas Zeller
Deploying machine learning in real-world systems necessitates methods to ensure trustworthy AI. This course explores research at the intersection of machine learning, privacy, and security. This course provides a comprehensive overview of techniques to build robust and trustworthy machine learning models, focusing on neural networks. We will examine seminal work on privacy-preserving machine learning methods. Our primary focus will be on Large Language Models (LLMs), Diffusion Models (DMs), and Image Autoregressive Models (IARs). Throughout the course, we will discuss outstanding challenges and future research directions to make machine learning more robust, private, and trustworthy.
Requirements: The course presumes a good understanding of machine learning. The students should have taken and passed a machine learning course. This seminar is open to senior Bachelor, Master, and Doctoral students. It is recommended for students who took the Trustworthy Machine Learning course last semester.
In this seminar, through seminal and recent papers, students will survey the emerging literature across research communities investigating the trustworthiness of machine learning. The class aims to inspire new research directions and applications. Lectures, slides, and research papers comprise the course materials (no textbook is required). By engaging with the latest work in this rapidly evolving field, students will be prepared to advance trustworthy machine learning.
Each student will present a paper during the seminar hours in the form of an oral presentation. In addition, each student will read the relevant papers for the other students’ presentations, and hand in a seminar paper summarizing their project at the end of the semester. Check this website for more information: https://cms.cispa.saarland/tml2526/
Places: 20