Joshua Kazdan

Publications

No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms. Joshua Kazdan, Abhay Puri, Rylan Schaeffer, Lisa Yu, Chris Cundy, Jason Stanley, Sanmi Koyejo, Krishnamurthy (Dj) Dvijotham. At International Conference on Learning Representations, 2026.

Article Citation Code

Silent Sabotage: Injecting Backdoors into AI Agents Through Fine-Tuning. Léo Boisvert, Abhay Puri, Chandra Kiran Reddy Evuru, Joshua Kazdan, Avinandan Bose, Quentin Cappart, Maryam Fazel, Sai Rajeswar Mudumba, Jason Stanley, Nicolas Chapados, Alexandre Drouin, Krishnamurthy (Dj) Dvijotham. At Workshop at the International Conference of Machine Learning (ICML), 2025.

Article Citation

No, of course I can! Refusal Mechanisms Can Be Exploited Using Harmless Fine-Tuning Data. Joshua Kazdan, Krishnamurthy (Dj) Dvijotham, Sanmi Koyejo. At Workshop at the International Conference of Learning Representation (ICLR), 2025.

Article Citation Vidéo