Research Group
Machine Learning
and Security
and Security
View from our building over Berlin.
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.
December 11, 2025 — We are honored and grateful to receive the Test-of-Time Award at ACSAC for our work on detecting JavaScript attacks. Thank you all so much! 🏆😊
October 15, 2025 — We are thrilled to receive the Distinguished Paper Award at CCS for our work on manipulating weather forecasts of AI models 🏆.
October 13, 2025 — We are attending CCS in Taipei, 🇹🇼. Erik is presenting our work on manipulating weather forecasts of AI models, and Anna is presenting a workshop paper on threat modeling for cloud applications.
October 1, 2025 — We are starting the winter semester with new courses, including our lecure on adversarial machine learning and projects on AI attacks and defenses. Register in the ISIS platform 📚.
See all news and updates of the research group.
A Large-Scale Study of Personalized Phishing using Large Language Models.
35th USENIX Security Symposium, 2026. (to appear)
LLM-based Vulnerability Discovery through the Lens of Code Metrics.
48th IEEE/ACM International Conference on Software Engineering (ICSE), 2026. (to appear)
Manipulating Feature Visualizations with Gradient Slingshots.
Advances in Neural Information Processing Systems 39 (NeurIPS), 2025.
Adversarial Observations in Weather Forecasting.
32nd ACM Conference on Computer and Communications Security (CCS), 2025.
Distinguished Paper Award
See all publications of the research group.
DISTEL — Differential Security Testing of LLMs
This project introduces differential security testing for LLMs. It aims to compare LLM behavior across model variants, software stacks, and hardware platforms. The goal is to assess whether differences can impact the security and trustworthiness of LLMs. The project is part of the excellence cluster CASA.
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.
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.
See all projects of the research group.
BIFOLD & TU Berlin
Machine Learning and Security (FR7-4)
Franklinstraße 28-29
10587 Berlin, Germany
Office: office@mlsec.tu-berlin.de
Responsibility under the German Press Law §55 Sect. 2 RStV:
Prof. Dr. Konrad Rieck