Papers

  • Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models - Winninger T., Addad B., Kapusta K. Mar 25. ArXiv

Talks

  • Mechanistic interpretability for LLM attack and defense, École Polytechnique, CeSIA, Apr 25. Slides

  • Introduction to AI security and reverse engineering, HackademINT, Apr 25. Slides / Webpage

  • Model Poisoning, Station F, CeSIA, Jun 24. Slides

  • GNN based IDS and its robustness against adversarial attacks, HackademINT, Jun 24. Slides

  • Cheating Detection in the 404 CTF, Rendez-vous de la Recherche et de l’Enseignement de la Sécurité des Systèmes d’Information (RESSI), May 24.

  • Introduction to prompt hacking, HackademINT, Nov 23. Slides

  • How to backdoor federated learning, HackademINT, May 23. Slides

  • Introduction to AI & cyber security, HackademINT, May 23. Slides

Misc

  • ZaMark: Intellectual Property protection with Homomorphic Watermarking, Privacy Preserving Hackathon, Zama, September 2024, (finished 2nd). Slides