← Authors

Nicolas Papernot

45 papers · 2018–2025 · 5 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (7) 🐝 Cross-Pollinator (8) 🌈 Renaissance Researcher (8) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (43) 🧭 Keyword Pioneer πŸ”¬ Deep Specialist (12) πŸ† Grand Slam πŸ‘‘ Triple Crown πŸ—ƒοΈ Keyword Collector (102) ⚑ Prolific Year (10) πŸš€ Conference Pioneer πŸ’Ž Century Club (45) πŸ”₯ Unstoppable (8) ❓ The Questioner (2)

Conferences

ICLR (15) NIPS (14) ICML (13) CVPR (2) AAAI (1)

Top co-authors

Adam Dziedzic (9) Muhammad Ahmad Kaleem (5) Xiao Wang (5) Ali Shahin Shamsabadi (5) Christopher A. Choquette-Choo (5) Florian Tramer (5) Nicholas Carlini (5) Ilia Shumailov (4) Stephan Rabanser (4) Franziska Boenisch (4)

Research topics

Privacy (5) Differential Privacy (2)

Keywords

differential privacy (8) adversarial attack (6) adversarial robustness (4) adversarial example (3) model robustness (3) membership inference (3) representation learning (2) stochastic gradient descent (2) adversarial machine learning (2) self-supervised learning (2) model extraction (2) dataset inference (2) backdoor attack (2) adversarial perturbation (2) large language model (2) ensemble learning (1) entropy minimization (1) training manipulation (1) adversarial optimization (1) adversarial learning (1)

Papers

Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses ICLR 2025
Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention ICML 2025
Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings ICML 2025
Leveraging Per-Instance Privacy for Machine Unlearning ICML 2025
Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model ICLR 2025
Language Models May Verbatim Complete Text They Were Not Explicitly Trained On ICML 2025
Fast Exact Unlearning for In-Context Learning Data for LLMs ICML 2025
Auditing Private Prediction ICML 2024
Confidential-DPproof: Confidential Proof of Differentially Private Training ICLR 2024
Memorization in Self-Supervised Learning Improves Downstream Generalization ICLR 2024
Temporal-Difference Learning Using Distributed Error Signals NIPS 2024
LLM Dataset Inference: Did you train on my dataset? NIPS 2024
The Fundamental Limits of Least-Privilege Learning ICML 2024
Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches ICML 2024
Robust and Actively Secure Serverless Collaborative Learning NIPS 2023
Confidential-PROFITT: Confidential PROof of FaIr Training of Trees ICLR 2023
Architectural Backdoors in Neural Networks CVPR 2023
Training Private Models That Know What They Don’t Know NIPS 2023
Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models NIPS 2023
Measuring Forgetting of Memorized Training Examples ICLR 2023
Have it your way: Individualized Privacy Assignment for DP-SGD NIPS 2023
Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning ICLR 2022
Dataset Inference for Self-Supervised Models NIPS 2022
The Privacy Onion Effect: Memorization is Relative NIPS 2022
Washing The Unwashable : On The (Im)possibility of Fairwashing Detection NIPS 2022
On the Limitations of Stochastic Pre-processing Defenses NIPS 2022
In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning NIPS 2022
A Zest of LIME: Towards Architecture-Independent Model Distances ICLR 2022
Hyperparameter Tuning with Renyi Differential Privacy ICLR 2022
Increasing the Cost of Model Extraction with Calibrated Proof of Work ICLR 2022
On the Difficulty of Defending Self-Supervised Learning against Model Extraction ICML 2022
Dataset Inference: Ownership Resolution in Machine Learning ICLR 2021
Data-Free Model Extraction CVPR 2021
Manipulating SGD with Data Ordering Attacks NIPS 2021
Label-Only Membership Inference Attacks ICML 2021
Markpainting: Adversarial Machine Learning meets Inpainting ICML 2021
Tempered Sigmoid Activations for Deep Learning with Differential Privacy AAAI 2021
CaPC Learning: Confidential and Private Collaborative Learning ICLR 2021
Thieves on Sesame Street! Model Extraction of BERT-based APIs ICLR 2020
Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations ICML 2020
MixMatch: A Holistic Approach to Semi-Supervised Learning NIPS 2019
Analyzing and Improving Representations with the Soft Nearest Neighbor Loss ICML 2019
Ensemble Adversarial Training: Attacks and Defenses ICLR 2018
Scalable Private Learning with PATE ICLR 2018
Adversarial Examples that Fool both Computer Vision and Time-Limited Humans NIPS 2018