Nicolas Papernot
~Nicolas_Papernot1
22
论文总数
11.0
年均投稿
平均评分
接收情况12/22
会议分布
ICLR
14
ICML
5
NeurIPS
3
发表论文 (22 篇)
20259 篇
4
What Does It Take to Build a Performant Selective Classifier?
NeurIPS 2025Poster
4
Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
ICLR 2025Poster
3
Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings
ICML 2025Oral
4
Fast Exact Unlearning for In-Context Learning Data for LLMs
ICML 2025Poster
5
Leveraging Per-Instance Privacy for Machine Unlearning
ICML 2025Poster
5
Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses
ICLR 2025Poster
3
Lossgate: Incomplete Information and Misaligned Incentives Hinder Regulation of Societal Risks in Machine Learning
ICLR 2025Rejected
3
Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
ICML 2025Poster
4
Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
ICML 2025Spotlight
202413 篇
5
The Fundamental Limits of Least-Privilege Learning
ICLR 2024Rejected
4
Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias
ICLR 2024Rejected
6
LLM Dataset Inference: Did you train on my dataset?
NeurIPS 2024Poster
4
Beyond Labeling Oracles: What does it mean to steal ML models?
ICLR 2024Rejected
3
Regulation Games for Trustworthy Machine Learning
ICLR 2024Rejected
4
LLM Censorship: The Problem and its Limitations
ICLR 2024Rejected
3
FairPATE: Exposing the Pareto Frontier of Fairness, Privacy, Accuracy, and Coverage
ICLR 2024Rejected
4
Beyond Laplace and Gaussian: Exploring the Generalized Gaussian Mechanism for Private Machine Learning
ICLR 2024Rejected
4
Temporal-Difference Learning Using Distributed Error Signals
NeurIPS 2024Poster
3
Local-Forward: Towards Biological Plausibility in Deep Reinforcement Learning
ICLR 2024Rejected
4
Memorization in Self-Supervised Learning Improves Downstream Generalization
ICLR 2024Poster
3
Confidential-DPproof: Confidential Proof of Differentially Private Training
ICLR 2024Spotlight
5
Selective Prediction via Training Dynamics
ICLR 2024Rejected