Nicolas Papernot

Most-cited papers

Machine Unlearning
Lucas Bourtoule, Varun Chandrasekaran, Christopher A. Choquette-Choo, Hengrui Jia +4 more
2019IEEE Symposium on Security and Privacy1,750 citations
Semantic Scholar
AI models collapse when trained on recursively generated data
Ilia Shumailov, Zakhar Shumaylov, Yi-Ren Zhao, Nicolas Papernot +2 more
2024Nature1,137 citations Open access
Semantic Scholar
The Curse of Recursion: Training on Generated Data Makes Models Forget
Ilia Shumailov, Zakhar Shumaylov, Yi-Ren Zhao, Yarin Gal +2 more
2023arXiv.org558 citations
Semantic Scholar
Unrolling SGD: Understanding Factors Influencing Machine Unlearning
Anvith Thudi, Gabriel Deza, Varun Chandrasekaran, Nicolas Papernot
2021European Symposium on Security and Privacy384 citations Open access
Semantic Scholar
Entangled Watermarks as a Defense against Model Extraction
Hengrui Jia, Christopher A. Choquette-Choo, Varun Chandrasekaran, Nicolas Papernot
2020USENIX Security Symposium323 citations
Semantic Scholar
When the Curious Abandon Honesty: Federated Learning Is Not Private
Franziska Boenisch, Adam Dziedzic, R. Schuster, A. Shamsabadi +2 more
2021European Symposium on Security and Privacy256 citations Open access
Semantic Scholar
On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning
Anvith Thudi, Hengrui Jia, Ilia Shumailov, Nicolas Papernot
2021USENIX Security Symposium247 citations
Semantic Scholar
Sponge Examples: Energy-Latency Attacks on Neural Networks
Ilia Shumailov, Yi-Ren Zhao, Daniel Bates, Nicolas Papernot +2 more
2020European Symposium on Security and Privacy216 citations Open access
Semantic Scholar
Dataset Inference: Ownership Resolution in Machine Learning
Pratyush Maini, Mohammad Yaghini, Nicolas Papernot
2021International Conference on Learning Representations181 citations
Semantic Scholar
LLM Dataset Inference: Did you train on my dataset?
Pratyush Maini, Hengrui Jia, Nicolas Papernot, Adam Dziedzic
2024Neural Information Processing Systems166 citations
Semantic Scholar
On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping
Sanghyun Hong, Varun Chandrasekaran, Yiğitcan Kaya, Tudor Dumitras +1 more
2020arXiv.org160 citations
Semantic Scholar
Proof-of-Learning: Definitions and Practice
Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud +3 more
2021IEEE Symposium on Security and Privacy151 citations
Semantic Scholar
Bad Characters: Imperceptible NLP Attacks
N. Boucher, Ilia Shumailov, Ross Anderson, Nicolas Papernot
2021IEEE Symposium on Security and Privacy150 citations Open access
Semantic Scholar
Manipulating SGD with Data Ordering Attacks
Ilia Shumailov, Zakhar Shumaylov, Dmitry Kazhdan, Yi-Ren Zhao +3 more
2021Neural Information Processing Systems125 citations
Semantic Scholar
Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models
Haonan Duan, Adam Dziedzic, Nicolas Papernot, Franziska Boenisch
2023Neural Information Processing Systems120 citations Open access
Semantic Scholar
Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
Jamie Hayes, Ilia Shumailov, Eleni Triantafillou, Amr Khalifa +1 more
20242025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)109 citations Open access
Semantic Scholar
Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias
Sierra Wyllie, Ilia Shumailov, Nicolas Papernot
2024Conference on Fairness, Accountability and Transparency92 citations Open access
Semantic Scholar
On the Robustness of Cooperative Multi-Agent Reinforcement Learning
Jieyu Lin, Kristina Dzeparoska, Sai Zhang, A. Leon-Garcia +1 more
20202020 IEEE Security and Privacy Workshops (SPW)90 citations Open access
Semantic Scholar
LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?
D. Glukhov, Ilia Shumailov, Yarin Gal, Nicolas Papernot +1 more
2023arXiv.org87 citations Open access
Semantic Scholar
On the Privacy Risk of In-context Learning
Haonan Duan, Adam Dziedzic, Mohammad Yaghini, Nicolas Papernot +1 more
2024arXiv.org75 citations
Semantic Scholar
CaPC Learning: Confidential and Private Collaborative Learning
Christopher A. Choquette-Choo, Natalie Dullerud, Adam Dziedzic, Yun-Xiang Zhang +3 more
2021International Conference on Learning Representations68 citations
Semantic Scholar
Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment
Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu +20 more
202366 citations
Semantic Scholar
UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
Ilia Shumailov, Jamie Hayes, Eleni Triantafillou, Guillermo Ortiz-Jiménez +5 more
2024arXiv.org65 citations
Semantic Scholar
Dataset Inference for Self-Supervised Models
Adam Dziedzic, Haonan Duan, Muhammad Ahmad Kaleem, Nikita Dhawan +4 more
2022Neural Information Processing Systems60 citations Open access
Semantic Scholar
Verifiable and Provably Secure Machine Unlearning
Thorsten Eisenhofer, Doreen Riepel, Varun Chandrasekaran, Esha Ghosh +2 more
20222025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)57 citations
Semantic Scholar
Differentially Private Speaker Anonymization
A. Shamsabadi, B. M. L. Srivastava, A. Bellet, Nathalie Vauquier +4 more
2022Proceedings on Privacy Enhancing Technologies56 citations Open access
Semantic Scholar
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice
A. Cooper, Christopher A. Choquette-Choo, Miranda Bogen, Matthew Jagielski +31 more
2024arXiv.org49 citations
Semantic Scholar
Architectural Backdoors in Neural Networks
Mikel Bober-Irizar, Ilia Shumailov, Yi-Ren Zhao, Robert D. Mullins +1 more
2022Computer Vision and Pattern Recognition47 citations
Semantic Scholar
Increasing the Cost of Model Extraction with Calibrated Proof of Work
Adam Dziedzic, Muhammad Ahmad Kaleem, Yu-Shen Lu, Nicolas Papernot
2022International Conference on Learning Representations42 citations
Semantic Scholar
Decentralised, collaborative, and privacy-preserving machine learning for multi-hospital data
Cong Fang, Adam Dziedzic, Lin Zhang, Laura Oliva +4 more
2024EBioMedicine41 citations Open access
Semantic Scholar
Have it your way: Individualized Privacy Assignment for DP-SGD
Franziska Boenisch, Christopher Muhl, Adam Dziedzic, Roy Rinberg +1 more
2023Neural Information Processing Systems41 citations Open access
Semantic Scholar
Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation
Franziska Boenisch, Adam Dziedzic, R. Schuster, A. Shamsabadi +2 more
2023European Symposium on Security and Privacy38 citations Open access
Semantic Scholar
On the Difficulty of Defending Self-Supervised Learning against Model Extraction
Adam Dziedzic, Nikita Dhawan, Muhammad Ahmad Kaleem, Jonas Guan +1 more
2022International Conference on Machine Learning36 citations Open access
Semantic Scholar
Confidential-PROFITT: Confidential PROof of FaIr Training of Trees
A. Shamsabadi, Sierra Wyllie, Nicholas Franzese, Natalie Dullerud +4 more
2023International Conference on Learning Representations35 citations
Semantic Scholar
On the Limitations of Stochastic Pre-processing Defenses
Yue Gao, Ilia Shumailov, K. Fawaz, Nicolas Papernot
2022Neural Information Processing Systems35 citations Open access
Semantic Scholar
Fast Exact Unlearning for In-Context Learning Data for LLMs
Andrei Muresanu, Anvith Thudi, Michael Zhang, Nicolas Papernot
2024International Conference on Machine Learning34 citations
Semantic Scholar
A Zest of LIME: Towards Architecture-Independent Model Distances
Hengrui Jia, Hongyu Chen, Jonas Guan, A. Shamsabadi +1 more
2022International Conference on Learning Representations34 citations
Semantic Scholar
Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment
Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu +20 more
2024Issue 6.1, Winter 202433 citations Open access
Semantic Scholar
Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
Ken Liu, Christopher A. Choquette-Choo, Matthew Jagielski, P. Kairouz +3 more
2025International Conference on Machine Learning32 citations
Semantic Scholar
Confidential-DPproof: Confidential Proof of Differentially Private Training
A. Shamsabadi, Gefei Tan, Tudor Cebere, A. Bellet +4 more
2024International Conference on Learning Representations31 citations
Semantic Scholar
Challenges towards the Next Frontier in Privacy
Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu +20 more
2023arXiv.org29 citations Open access
Semantic Scholar
Selective Prediction via Training Dynamics
Stephan Rabanser, Anvith Thudi, K. Hamidieh, Adam Dziedzic +4 more
2022Trans. Mach. Learn. Res.29 citations
Semantic Scholar
Proof-of-Learning is Currently More Broken Than You Think
Cong Fang, Hengrui Jia, Anvith Thudi, Mohammad Yaghini +4 more
2022European Symposium on Security and Privacy28 citations Open access
Semantic Scholar
Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
Tudor Cebere, A. Bellet, Nicolas Papernot
2024International Conference on Learning Representations26 citations
Semantic Scholar
Washing The Unwashable : On The (Im)possibility of Fairwashing Detection
A. Shamsabadi, Mohammad Yaghini, Natalie Dullerud, Sierra Wyllie +4 more
2022Neural Information Processing Systems24 citations
Semantic Scholar
Towards More Robust Keyword Spotting for Voice Assistants
Shimaa Ahmed, Ilia Shumailov, Nicolas Papernot, K. Fawaz
2022USENIX Security Symposium24 citations
Semantic Scholar
Memorization in Self-Supervised Learning Improves Downstream Generalization
Wen-Hao Wang, Muhammad Ahmad Kaleem, Adam Dziedzic, Michael Backes +2 more
2024International Conference on Learning Representations23 citations
Semantic Scholar
CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
Hanna Foerster, Robert Mullins, Tom Blanchard, Nicolas Papernot +5 more
2026arXiv.org22 citations
Semantic Scholar
SoK: Machine Learning Governance
Varun Chandrasekaran, Hengrui Jia, Anvith Thudi, Adelin Travers +2 more
2021arXiv.org22 citations
Semantic Scholar
Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
Anvith Thudi, Hengrui Jia, Casey Meehan, Ilia Shumailov +1 more
2023USENIX Security Symposium21 citations Open access
Semantic Scholar