Nicolas Papernot
7
Papers
14
Total Citations
Papers (7)
Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses
ICLR 2025arXiv
10
citations
Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
ICML 2025
2
citations
Leveraging Per-Instance Privacy for Machine Unlearning
ICML 2025
1
citations
Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings
ICML 2025
1
citations
The Fundamental Limits of Least-Privilege Learning
ICML 2024
0
citations
Auditing Private Prediction
ICML 2024
0
citations
Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches
ICML 2024
0
citations