Nicolas Papernot

7

Papers

14

Total Citations

Papers (7)

Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

Leveraging Per-Instance Privacy for Machine Unlearning

Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings

The Fundamental Limits of Least-Privilege Learning

Auditing Private Prediction

Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches