Glukhov, David

3 publications

ICLR 2025 Breach by a Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses David Glukhov, Ziwen Han, Ilia Shumailov, Vardan Papyan, Nicolas Papernot

TMLR 2024 Augment Then Smooth: Reconciling Differential Privacy with Certified Robustness Jiapeng Wu, Atiyeh Ashari Ghomi, David Glukhov, Jesse C. Cresswell, Franziska Boenisch, Nicolas Papernot

ICML 2024 Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches David Glukhov, Ilia Shumailov, Yarin Gal, Nicolas Papernot, Vardan Papyan