Nicolas Papernot
University of Toronto
H-index: 51
North America-Canada
Top articles of Nicolas Papernot
Title | Journal | Author(s) | Publication Date |
|---|---|---|---|
Unlearnable algorithms for in-context learning | arXiv preprint arXiv:2402.00751 | Andrei Muresanu Anvith Thudi Michael R Zhang Nicolas Papernot | 2024/2/1 |
Inexact unlearning needs more careful evaluations to avoid a false sense of privacy | arXiv preprint arXiv:2403.01218 | Jamie Hayes Ilia Shumailov Eleni Triantafillou Amr Khalifa Nicolas Papernot | 2024/3/2 |
Memorization in self-supervised learning improves downstream generalization | arXiv preprint arXiv:2401.12233 | Wenhao Wang Muhammad Ahmad Kaleem Adam Dziedzic Michael Backes Nicolas Papernot | 2024/1/19 |
Decentralised, collaborative, and privacy-preserving machine learning for multi-hospital data | EBioMedicine | Congyu Fang Adam Dziedzic Lin Zhang Laura Oliva Amol Verma | 2024/3/1 |
Advancing differential privacy: Where we are now and future directions for real-world deployment | Rachel Cummings Damien Desfontaines David Evans Roxana Geambasu Yangsibo Huang | 2024/1/16 | |
Auditing Private Prediction | arXiv preprint arXiv:2402.09403 | Karan Chadha Matthew Jagielski Nicolas Papernot Christopher Choquette-Choo Milad Nasr | 2024/2/14 |
Robust and Actively Secure Serverless Collaborative Learning | Advances in Neural Information Processing Systems (NeurIPS) | Olive Franzese* Adam Dziedzic* Christopher A Choquette-Choo Mark R Thomas Muhammad Ahmad Kaleem | 2023/10/25 |
Neural network training using the soft nearest neighbor loss | 2024/3/26 | ||
Architectural Neural Backdoors from First Principles | arXiv preprint arXiv:2402.06957 | Harry Langford Ilia Shumailov Yiren Zhao Robert Mullins Nicolas Papernot | 2024/2/10 |
Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias | arXiv preprint arXiv:2403.07857 | Sierra Wyllie Ilia Shumailov Nicolas Papernot | 2024/3/12 |
Beyond Laplace and Gaussian: Exploring the Generalized Gaussian Mechanism for Private Machine Learning | Roy Rinberg Ilia Shumailov Rachel Cummings Nicolas Papernot | 2023/10/13 | |
The Adversarial Implications of Variable-Time Inference | Dudi Biton Aditi Misra Efrat Levy Jaidip Kotak Ron Bitton | 2023/11/30 | |
Augment then Smooth: Reconciling Differential Privacy with Certified Robustness | arXiv preprint arXiv:2306.08656 | Jiapeng Wu Atiyeh Ashari Ghomi David Glukhov Jesse C Cresswell Franziska Boenisch | 2023/6/14 |
Differentially private speaker anonymization | Privacy Enhancing Technologies Symposium | Ali Shahin Shamsabadi Brij Mohan Lal Srivastava Aurélien Bellet Nathalie Vauquier Emmanuel Vincent | 2022/2/23 |
Have it your way: Individualized Privacy Assignment for DP-SGD | 37th Conference on Neural Information Processing Systems | Franziska Boenisch Christopher Mühl Adam Dziedzic Roy Rinberg Nicolas Papernot | 2023/3/29 |
Losing less: A loss for differentially private deep learning | Proceedings on Privacy Enhancing Technologies | Ali Shahin Shamsabadi Nicolas Papernot | 2023 |
When Vision Fails: Text Attacks Against ViT and OCR | arXiv preprint arXiv:2306.07033 | Nicholas Boucher Jenny Blessing Ilia Shumailov Ross Anderson Nicolas Papernot | 2023/6/12 |
FairPATE: Exposing the Pareto Frontier of Fairness, Privacy, Accuracy, and Coverage | Mohammad Yaghini Patty Liu Franziska Boenisch Nicolas Papernot | 2023/10/13 | |
Subtle adversarial image manipulations influence both human and machine perception | Nature Communications | Vijay Veerabadran Josh Goldman Shreya Shankar Brian Cheung Nicolas Papernot | 2023/8/15 |
Sentence embedding encoders are easy to steal but hard to defend | Adam Dziedzic Franziska Boenisch Mingjian Jiang Haonan Duan Nicolas Papernot | 2023/3/4 |
Co-Authors
