David Glukhov
PhD student
Email
Papers
- A False Sense of Safety: Unsafe Information Leakage in Safe AI Responses
David Glukhov, Ziwen Han, Ilia Shumailov, Vardan Papyan, Nicolas Papernot
In Proceedings of the 13th International Conference on Learning Representations@inproceedings{david2025aconference, author = {Glukhov, David and Han, Ziwen and Shumailov, Ilia and Papyan, Vardan and Papernot, Nicolas}, booktitle = {Proceedings of the 13th International Conference on Learning Representations}, title = {A False Sense of Safety: Unsafe Information Leakage in Safe AI Responses}, year = {2025} }
- Preempt: Sanitizing Sensitive Prompts for LLMs
Amrita Roy Chowdhury, David Glukhov, Divyam Anshumaan, Prasad Chalasani, Nicolas Papernot, Somesh Jha
@article{amrita2024preemptworkshop, author = {Chowdhury, Amrita Roy and Glukhov, David and Anshumaan, Divyam and Chalasani, Prasad and Papernot, Nicolas and Jha, Somesh}, title = {Preempt: Sanitizing Sensitive Prompts for LLMs}, year = {2024} }
- Position Paper: Rethinking LLM Censorship as a Security Problem
David Glukhov, Ilia Shumailov, Yarin Gal, Nicolas Papernot, Vardan Papyan
In Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria@inproceedings{david2024positionconference, author = {Glukhov, David and Shumailov, Ilia and Gal, Yarin and Papernot, Nicolas and Papyan, Vardan}, booktitle = {Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria}, title = {Position Paper: Rethinking LLM Censorship as a Security Problem}, year = {2024} }
- Augment then Smooth: Reconciling Differential Privacy with Certified Robustness
Jiapeng Wu, Atiyeh Ashari Ghomi, David Glukhov, Jesse C. Cresswell, Franziska Boenisch, Nicolas Papernot
@article{jiapeng2024augmentjournal, author = {Wu, Jiapeng and Ghomi, Atiyeh Ashari and Glukhov, David and Cresswell, Jesse C. and Boenisch, Franziska and Papernot, Nicolas}, title = {Augment then Smooth: Reconciling Differential Privacy with Certified Robustness}, year = {2024} }