Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Nicolas Papernot

On the Exploitability of Audio Machine Learning Pipelines to Surreptitious Adversarial Examples


Aug 03, 2021
Adelin Travers, Lorna Licollari, Guanghan Wang, Varun Chandrasekaran, Adam Dziedzic, David Lie, Nicolas Papernot


  Access Paper or Ask Questions

Bad Characters: Imperceptible NLP Attacks


Jun 18, 2021
Nicholas Boucher, Ilia Shumailov, Ross Anderson, Nicolas Papernot


  Access Paper or Ask Questions

Markpainting: Adversarial Machine Learning meets Inpainting


Jun 01, 2021
David Khachaturov, Ilia Shumailov, Yiren Zhao, Nicolas Papernot, Ross Anderson

* Proceedings of the 38th International Conference on Machine Learning (ICML 2021) 

  Access Paper or Ask Questions

Dataset Inference: Ownership Resolution in Machine Learning


Apr 21, 2021
Pratyush Maini, Mohammad Yaghini, Nicolas Papernot

* Published as a conference paper at ICLR 2021 (Spotlight Presentation) 

  Access Paper or Ask Questions

Manipulating SGD with Data Ordering Attacks


Apr 19, 2021
Ilia Shumailov, Zakhar Shumaylov, Dmitry Kazhdan, Yiren Zhao, Nicolas Papernot, Murat A. Erdogdu, Ross Anderson


  Access Paper or Ask Questions

Proof-of-Learning: Definitions and Practice


Mar 09, 2021
Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Anvith Thudi, Varun Chandrasekaran, Nicolas Papernot

* To appear in the 42nd IEEE Symposium on Security and Privacy 

  Access Paper or Ask Questions

CaPC Learning: Confidential and Private Collaborative Learning


Feb 09, 2021
Christopher A. Choquette-Choo, Natalie Dullerud, Adam Dziedzic, Yunxiang Zhang, Somesh Jha, Nicolas Papernot, Xiao Wang

* Published as a conference paper at ICLR 2021 

  Access Paper or Ask Questions

Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning


Jan 11, 2021
Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Nicholas Carlini


  Access Paper or Ask Questions

Neighbors From Hell: Voltage Attacks Against Deep Learning Accelerators on Multi-Tenant FPGAs


Dec 14, 2020
Andrew Boutros, Mathew Hall, Nicolas Papernot, Vaughn Betz

* Published in the 2020 proceedings of the International Conference of Field-Programmable Technology (ICFPT) 

  Access Paper or Ask Questions

Data-Free Model Extraction


Nov 30, 2020
Jean-Baptiste Truong, Pratyush Maini, Robert Walls, Nicolas Papernot


  Access Paper or Ask Questions

Adversarial Examples in Constrained Domains


Nov 02, 2020
Ryan Sheatsley, Nicolas Papernot, Michael Weisman, Gunjan Verma, Patrick McDaniel

* 17 pages, 5 figures 

  Access Paper or Ask Questions

Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings


Oct 13, 2020
Vinith M. Suriyakumar, Nicolas Papernot, Anna Goldenberg, Marzyeh Ghassemi


  Access Paper or Ask Questions

Not My Deepfake: Towards Plausible Deniability for Machine-Generated Media


Aug 20, 2020
Baiwu Zhang, Jin Peng Zhou, Ilia Shumailov, Nicolas Papernot


  Access Paper or Ask Questions

Label-Only Membership Inference Attacks


Jul 28, 2020
Christopher A. Choquette Choo, Florian Tramer, Nicholas Carlini, Nicolas Papernot

* 16 pages, 11 figures, 2 tables 

  Access Paper or Ask Questions

Tempered Sigmoid Activations for Deep Learning with Differential Privacy


Jul 28, 2020
Nicolas Papernot, Abhradeep Thakurta, Shuang Song, Steve Chien, Úlfar Erlingsson


  Access Paper or Ask Questions

SoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systems


Jul 21, 2020
Hadi Abdullah, Kevin Warren, Vincent Bindschaedler, Nicolas Papernot, Patrick Traynor


  Access Paper or Ask Questions

The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systems


Jul 13, 2020
Hadi Abdullah, Kevin Warren, Vincent Bindschaedler, Nicolas Papernot, Patrick Traynor


  Access Paper or Ask Questions

Sponge Examples: Energy-Latency Attacks on Neural Networks


Jun 05, 2020
Ilia Shumailov, Yiren Zhao, Daniel Bates, Nicolas Papernot, Robert Mullins, Ross Anderson


  Access Paper or Ask Questions

On the Robustness of Cooperative Multi-Agent Reinforcement Learning


Mar 08, 2020
Jieyu Lin, Kristina Dzeparoska, Sai Qian Zhang, Alberto Leon-Garcia, Nicolas Papernot


  Access Paper or Ask Questions

On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping


Feb 27, 2020
Sanghyun Hong, Varun Chandrasekaran, Yiğitcan Kaya, Tudor Dumitraş, Nicolas Papernot


  Access Paper or Ask Questions

Entangled Watermarks as a Defense against Model Extraction


Feb 27, 2020
Hengrui Jia, Christopher A. Choquette-Choo, Nicolas Papernot


  Access Paper or Ask Questions

Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations


Feb 11, 2020
Florian Tramèr, Jens Behrmann, Nicholas Carlini, Nicolas Papernot, Jörn-Henrik Jacobsen

* Supersedes the workshop paper "Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness" (arXiv:1903.10484) 

  Access Paper or Ask Questions

Machine Unlearning


Dec 09, 2019
Lucas Bourtoule, Varun Chandrasekaran, Christopher Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, Nicolas Papernot


  Access Paper or Ask Questions

Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications


Oct 29, 2019
Nicholas Carlini, Úlfar Erlingsson, Nicolas Papernot


  Access Paper or Ask Questions

Thieves on Sesame Street! Model Extraction of BERT-based APIs


Oct 27, 2019
Kalpesh Krishna, Gaurav Singh Tomar, Ankur P. Parikh, Nicolas Papernot, Mohit Iyyer

* preprint, 18 pages 

  Access Paper or Ask Questions

Improving Differentially Private Models with Active Learning


Oct 02, 2019
Zhengli Zhao, Nicolas Papernot, Sameer Singh, Neoklis Polyzotis, Augustus Odena


  Access Paper or Ask Questions

High-Fidelity Extraction of Neural Network Models


Sep 03, 2019
Matthew Jagielski, Nicholas Carlini, David Berthelot, Alex Kurakin, Nicolas Papernot


  Access Paper or Ask Questions

How Relevant is the Turing Test in the Age of Sophisbots?


Aug 30, 2019
Dan Boneh, Andrew J. Grotto, Patrick McDaniel, Nicolas Papernot


  Access Paper or Ask Questions

MixMatch: A Holistic Approach to Semi-Supervised Learning


May 06, 2019
David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, Colin Raffel


  Access Paper or Ask Questions