From privacy leaks in rail transport to the security of AI agents: BIFOLD contributes five papers to a leading forum for computer security research
At the 33rd ACM Conference on Computer and Communications Security (ACM CCS 2026), BIFOLD researchers will contribute five papers. The conference will take place in The Hague, Netherlands, from November 15 to 19, 2026. Two papers are for the main conference. Three are for the 19th ACM Workshop on Artificial Intelligence and Security (AISec 2026). Two of the workshop papers have been selected for spotlight presentations.
All five papers were co-authored by researchers from BIFOLD's Machine Learning and Security group, led by Konrad Rieck.
The ACM Conference on Computer and Communications Security (CCS) is the annual conference of the Association for Computing Machinery’s Special Interest Group on Security, Audit and Control (SIGSAC). It brings together information security researchers, practitioners, developers, and users from around the world to share new ideas and results.
BIFOLD is pleased to contribute to the ACM CCS 2026 program. Below is an overview of BIFOLD's contributions:
On the Same Track: Privacy Leaks in Electric Rail Transport via Magnetic Fields
- Authors: Stefan Czybik, Pia Hanfeld, Konrad Rieck
- Paper: https://www.mlsec.tu-berlin.de/docs/2026b-ccs.pdf
- Code: https://github.com/mlsec-group/magtrack
- Dataset: https://zenodo.org/records/22206115
- Presentation: Monday, November 16, 2026, 11:00 to 12:30, Session B6: Attacks on Privacy
- Presenter: Stefan Czybik
Hello Again: Exploiting Replay Protected Monotonic Counters to Brute-Force Windows Hello PINs
- Christian Werling, Matti Finder, Hans Niklas Jacob, Julian Prein, Niclas Kühnapfel, Jean-Pierre Seifert
- Paper: https://arxiv.org/abs/2611.18126
- Code: https://github.com/mattifinder/rpmc_attacks
- Presentation: Tuesday, November 17, 2026, 10:30 to 12:30, Session D6: Hardware security
- Presenter: Christian Werling, Julian Prein
Secrets Everywhere: Auditing Memorization in Mobility Prediction Models
- Authors: Anne Josiane Kouam, Hristo Boyadzhiev, Konrad Rieck
- Paper: https://www.mlsec.tu-berlin.de/docs/2026a-ccs.pdf
- Presentation: Wednesday, November 18, 2026, 10:30 to 12:30, Session H6: Privacy in Machine Learning
- Presenter: Anne Josiane Kouam
Track: Security/Privacy of AI
Controlling Autonomous Vehicles using Continuous Adversarial Patches
- Authors: Pia Hanfeld, Erik Imgrund, Felix Weissberg, Thorsten Eisenhofer, Wolfgang Hönig, Konrad Rieck
- Selected for a spotlight presentation
- Paper: https://www.mlsec.tu-berlin.de/docs/2026b-aisec.pdf
- Code: https://github.com/mlsec-group/continuous-patches
- Presentation: AISec 2026, November 15, 2026
False Prophets: On the Security of World Models in Agentic Systems
- Authors: Erik Imgrund, Anna Wimbauer, Klim Kireev, Konrad Rieck
- Selected for a spotlight presentation
- Paper: https://www.mlsec.tu-berlin.de/docs/2026a-aisec.pdf
- Code: https://github.com/mlsec-group/worldmodel-security
- Presentation: AISec 2026, November 15, 2026
Track: AI for Security/Privacy
Data Augmentation in Learning-Based Binary Code Analysis
- Authors: Lennart Stülpnagel, Felix Weissberg, Jonas Möller, Benjamin Greb, Thorsten Eisenhofer, Konrad Rieck
- Paper: https://mlsec.org/docs/2026c-aisec.pdf
- Code: github.com/mlsec-group/laica
- Presentation: AISec 2026, November 15, 2026