Research Group
Machine Learning
and Security
View from our building over Berlin.

Welcome and Overview

Our research group conducts fundamental research at the intersection of computer security and machine learning. On the one end, we are interested in developing intelligent systems that can learn to protect computers from attacks and identify security problems automatically. On the other end, we explore the security and privacy of machine learning by developing novel attacks and defenses.

We are part of the Berlin Institute for the Foundations of Learning and Data (BIFOLD) at Technische Universität Berlin. Previously, we have been working at Technische Universität Braunschweig and the University of Göttingen.

News and Updates

March 1, 2025 — We welcome Pia Hanfeld as our new PhD student. 👋 Welcome aboard, Pia! We look forward to soaring to new heights in drone security and adversarial learning.

January 6, 2025 — There are 10 open PhD student positions in the BIFOLD Graduate School! Further details are available here. The deadline for application is February 3, 2025.

December 11, 2024 — We are attending ACSAC in Hawaii, 🇺🇸. Alex is presenting our paper on implanting machine learning backdoors into hardware, such as FPGAs and GPUs.

October 1, 2024 — We welcome Erik Imgrund as our new PhD student. 👋 Welcome aboard, Erik! We look forward to an exciting research journey together.

See all news and updates of the research group.

Teaching in Summer

MLSEC — Machine Learning for Computer Security

This integrated lecture is concerned with using machine learning in computer security. Many tasks in security, such as the analysis of malicious software or the discovery of vulnerabilities, rest on manual work. Methods from machine learning can help accelerate this process and make security systems more intelligent. The lecture explores different approaches for constructing such learning-based security systems.

   Course Website    Module 41101 Type: Lecture Audience: Master

SECLAB — Applied Security Lab

This lab is a hands-on, entry-level course that explores the security analysis of systems. It provides an introduction to practical system security and serves a preparation for later advanced security labs. This includes developing strategies and tools for security analysis as well as investigating the security of real-world systems. In each unit of the lab, a different system is analyzed, ranging from Android applications to network hosts.

   Course Website    Module 41100 Type: Lab course Audience: Bachelor, Master

See all teaching course.

Recent publications

Seeing through: Analyzing and Attacking Virtual Backgrounds in Video Calls.
Felix Weissberg, Jan-Malte Hilgefort, Steve Grogorick, Daniel Arp, Thorsten Eisenhofer, Martin Eisemann and Konrad Rieck.
Proc. of the 34th USENIX Security Symposium, 2025. (to appear)

PDF

Evil from Within: Machine Learning Backdoors Through Dormant Hardware Trojans.
Alexander Warnecke, Julian Speith, Jan-Niklas Möller, Konrad Rieck and Christof Paar.
Proc. of the 40th Annual Computer Security Applications Conference (ACSAC), 2024.

PDF

Pitfalls in Machine Learning for Computer Security.
Daniel Arp, Erwin Quiring, Feargus Pendlebury, Alexander Warnecke, Fabio Pierazzi, Christian Wressnegger, Lorenzo Cavallaro and Konrad Rieck.
Communications of the ACM, 67, (11), 2024.

PDF Link

Dancer in the Dark: Synthesizing and Evaluating Polyglots for Blind Cross-Site Scripting.
Robin Kirchner, Jonas Möller, Marius Musch, David Klein, Konrad Rieck and Martin Johns.
Proc. of the 33rd USENIX Security Symposium, 2024.
Distinguished Paper Award

PDF Code

See all publications of the research group.

Current projects

AIGENCY — Opportunities and Risks of Generative AI in Security

The project aims to systematically investigate the opportunities and risks of generative artificial intelligence in computer security. It explores generative models as a new tool as well as a new threat. The project is joint work with Fraunhofer AISEC, CISPA, FU Berlin, and Aleph Alpha.

BMBF 2023 – 2026

MALFOY — Machine Learning for Offensive Computer Security

The ERC Consolidator Grant MALFOY explores the application of machine learning in offensive computer security. It is an effort to understand how learning algorithms can be used by attackers and how this threat can be effectively mitigated.

ERC 2023 – 2028 Website

ALISON — Attacks against Machine Learning in Structured Domains

The goal of this project is to investigate the security of learning algorithms in structured domains. That is, the project develops a better understanding of attacks and defenses that operate in the problem space of learning algorithms rather than the feature space.

DFG 2023 – 2026

See all projects of the research group.

Contact

Technische Universität Berlin
Machine Learning and Security, TEL 8-2
Hardenbergstr. 40A
10623 Berlin, Germany

Office: office@mlsec.tu-berlin.de
Responsibility under the German Press Law §55 Sect. 2 RStV:
Prof. Dr. Konrad Rieck