Nicolas Papernot

发表

Technical Report on the CleverHans v2.1.0 Adversarial Examples Library

Ian J. Goodfellow, Jonas Rauber, Nicolas Papernot, 2016 .

CaPC Learning: Confidential and Private Collaborative Learning pdf

Christopher A. Choquette-Choo, Nicolas Papernot, Natalie Dullerud, 2021, ICLR 2021 Poster.

Dataset Inference: Ownership Resolution in Machine Learning pdf

Nicolas Papernot, Pratyush Maini, Mohammad Yaghini, 2021, ICLR 2021 Spotlight.

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

Marzyeh Ghassemi, Nicolas Papernot, Anna Goldenberg, 2020, FAccT.

Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks

Ananthram Swami, Somesh Jha, Xi Wu, 2015, 2016 IEEE Symposium on Security and Privacy (SP).

Practical Black-Box Attacks against Machine Learning

Ananthram Swami, Somesh Jha, Patrick D. McDaniel, 2016, AsiaCCS.

Ensemble Adversarial Training: Attacks and Defenses pdf

Dan Boneh, Patrick McDaniel, Nicolas Papernot, 2017, ICLR.

Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness pdf

Jörn-Henrik Jacobsen, Nicholas Carlini, Nicolas Papernot, 2019, ArXiv.

Adversarial Attacks on Neural Network Policies pdf

Sandy H. Huang, Pieter Abbeel, Nicolas Papernot, 2017, ICLR.

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

Dan Boneh, Patrick McDaniel, Nicolas Papernot, 2019, IEEE Security & Privacy.

Machine Unlearning pdf

David Lie, Nicolas Papernot, Varun Chandrasekaran, 2019, 2021 IEEE Symposium on Security and Privacy (SP).

Adversarial Vision Challenge pdf

Matthias Bethge, Marcel Salathé, Wieland Brendel, 2018, The NeurIPS '18 Competition.

The Limitations of Deep Learning in Adversarial Settings

Ananthram Swami, Somesh Jha, Patrick D. McDaniel, 2015, 2016 IEEE European Symposium on Security and Privacy (EuroS&P).

A ug 2 01 7 On the Protection of Private Information in Machine Learning Systems : Two Recent Approaches ( Invited Paper )

Ian J. Goodfellow, Nicolas Papernot, H. B. McMahan, 2018 .

The Space of Transferable Adversarial Examples pdf

Dan Boneh, Patrick D. McDaniel, Nicolas Papernot, 2017, ArXiv.

Adversarial Examples that Fool both Human and Computer Vision pdf

Jascha Sohl-Dickstein, Brian Cheung, Nicolas Papernot, 2018, ArXiv.

Making machine learning robust against adversarial inputs

Patrick D. McDaniel, Nicolas Papernot, Ian J. Goodfellow, 2018, Commun. ACM.

On the (Statistical) Detection of Adversarial Examples pdf

Patrick D. McDaniel, Michael Backes, Nicolas Papernot, 2017, ArXiv.

Crafting adversarial input sequences for recurrent neural networks

Ananthram Swami, Patrick D. McDaniel, Nicolas Papernot, 2016, MILCOM 2016 - 2016 IEEE Military Communications Conference.

On the Protection of Private Information in Machine Learning Systems: Two Recent Approches

Martín Abadi, Úlfar Erlingsson, Li Zhang, 2017, 2017 IEEE 30th Computer Security Foundations Symposium (CSF).

Adversarial Forces of Physical Models

Ian J. Goodfellow, A. Madry, Jonas Rauber, 2020 .

On Evaluating Adversarial Robustness 2 Principles of Rigorous Evaluations 2

Ian J. Goodfellow, A. Madry, Jonas Rauber, 2019 .

Poster: Extending Defensive Distillation

Nicolas Papernot, P. Mcdaniel, 2017 .

Increasing the Cost of Model Extraction with Calibrated Proof of Work

Nicolas Papernot, Adam Dziedzic, Muhammad Ahmad Kaleem, 2022, ArXiv.

Tempered Sigmoid Activations for Deep Learning with Differential Privacy pdf

Úlfar Erlingsson, Steve Chien, Shuang Song, 2020, AAAI.

Practical Black-Box Attacks against Deep Learning Systems using Adversarial Examples pdf

Ananthram Swami, Somesh Jha, Patrick D. McDaniel, 2016, ArXiv.

ON NEURAL NETWORK POLICIES

Sandy H. Huang, Ian J. Goodfellow, Nicolas Papernot, 2017 .

Label-Only Membership Inference Attacks

Nicholas Carlini, Nicolas Papernot, Florian Tramèr, 2020, ICML.

Challenges of Differentially Private Prediction in Healthcare Settings

Nicolas Papernot, V. Suriyakumar, A. Goldenberg, 2020 .

Detection under Privileged Information ( Full Paper ) ∗

Nicolas Papernot, Ryan Sheatsley, Z. B. Celik, 2018 .

Adversarial examples influence human visual perception

Ian Goodfellow, Jascha Sohl-Dickstein, Brian Cheung, 2019, Journal of Vision.

Making the Shoe Fit: Architectures, Initializations, and Tuning for Learning with Privacy

Shuang Song, Abhradeep Thakurta, Nicolas Papernot, 2019 .

Prototypical Examples in Deep Learning: Metrics, Characteristics, and Utility

Nicholas Carlini, Nicolas Papernot, Úlfar Erlingsson, 2018 .

Bad Characters: Imperceptible NLP Attacks pdf

Nicolas Papernot, Ross Anderson, Ilia Shumailov, 2021, 2022 IEEE Symposium on Security and Privacy (SP).

Measuring Forgetting of Memorized Training Examples

Florian Tramèr, Nicolas Papernot, Nicholas Carlini, 2022, ArXiv.

Intrinsic Anomaly Detection for Multi-Variate Time Series

Nicolas Papernot, Kashif Rasul, Jan Gasthaus, 2022, ArXiv.

On the Limitations of Stochastic Pre-processing Defenses

Nicolas Papernot, Ilia Shumailov, Kassem Fawaz, 2022, ArXiv.

Towards More Robust Keyword Spotting for Voice Assistants

Nicolas Papernot, Ilia Shumailov, Kassem Fawaz, 2022, USENIX Security Symposium.

On the Difficulty of Defending Self-Supervised Learning against Model Extraction

Nicolas Papernot, Adam Dziedzic, Muhammad Ahmad Kaleem, 2022, ICML.

Architectural Backdoors in Neural Networks

Robert D. Mullins, Nicolas Papernot, R. Mullins, 2022, ArXiv.

On the Fundamental Limits of Formally (Dis)Proving Robustness in Proof-of-Learning

Christopher A. Choquette-Choo, Nicolas Papernot, Varun Chandrasekaran, 2022, ArXiv.

Efficient Adversarial Training With Data Pruning

Robert D. Mullins, Nicolas Papernot, R. Mullins, 2022, ArXiv.

Dataset Inference for Self-Supervised Models

Nicolas Papernot, Adam Dziedzic, Muhammad Ahmad Kaleem, 2022, arXiv.org.

Adversarial Examples in Constrained Domains

Nicolas Papernot, Ryan Sheatsley, P. Mcdaniel, 2020, ArXiv.

Increasing the Cost of Model Extraction with Calibrated Proof of Work

Nicolas Papernot, Adam Dziedzic, Muhammad Ahmad Kaleem, 2022, ICLR.

Technical Report on the CleverHans v2.1.0 Adversarial Examples Library

Ian J. Goodfellow, Tom B. Brown, Jonas Rauber, 2016, 1610.00768.

On The Integrity Of Deep Learning Systems In Adversarial Settings

Nicolas Papernot, Nicolas Papernot, 2016 .

In Differential Privacy, There is Truth: On Vote Leakage in Ensemble Private Learning

Nicolas Papernot, D. Lie, Ilia Shumailov, 2022, NeurIPS.

Bounding Membership Inference

Nicolas Papernot, Ilia Shumailov, Franziska Boenisch, 2022, arXiv.org.

Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Search

Christopher A. Choquette-Choo, Nicolas Papernot, Abhradeep Thakurta, 2022, ArXiv.

Verifiable and Provably Secure Machine Unlearning

Nicolas Papernot, Varun Chandrasekaran, O. Ohrimenko, 2022, ArXiv.

Dataset Inference for Self-Supervised Models

Nicolas Papernot, Adam Dziedzic, Muhammad Ahmad Kaleem, 2022, arXiv.org.

Learned Systems Security

Nicolas Papernot, Thorsten Eisenhofer, Paul Grubbs, 2022, 2212.10318.

Learned Systems Security

Nicolas Papernot, Thorsten Eisenhofer, Paul Grubbs, 2022, ArXiv.

Adversarial Examples in Machine Learning

Nicolas Papernot, Nicolas Papernot, 2017 .

Detection under Privileged Information

Ananthram Swami, Rauf Izmailov, Patrick D. McDaniel, 2016, AsiaCCS.

Extending Detection with Forensic Information

Nicolas Papernot, A. Swami, P. Mcdaniel, 2016 .

High Accuracy and High Fidelity Extraction of Neural Networks

Nicolas Papernot, Nicholas Carlini, David Berthelot, 2019, USENIX Security Symposium.

High-Fidelity Extraction of Neural Network Models pdf

David Berthelot, Nicholas Carlini, Nicolas Papernot, 2019, ArXiv.

Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning pdf

Patrick D. McDaniel, Nicolas Papernot, Nicolas Papernot, 2018, ArXiv.

MixMatch: A Holistic Approach to Semi-Supervised Learning

David Berthelot, Colin Raffel, Nicholas Carlini, 2019, NeurIPS.

On the Effectiveness of Defensive Distillation pdf

Patrick D. McDaniel, Nicolas Papernot, Nicolas Papernot, 2016, ArXiv.

Analyzing and Improving Representations with the Soft Nearest Neighbor Loss

Geoffrey E. Hinton, Nicolas Papernot, Nicholas Frosst, 2019, ICML.

Manipulating SGD with Data Ordering Attacks pdf

Murat A. Erdogdu, Nicolas Papernot, Ross Anderson, 2021, NeurIPS.

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans

Jascha Sohl-Dickstein, Brian Cheung, Nicolas Papernot, 2018, NeurIPS.

Extending Defensive Distillation pdf

Patrick D. McDaniel, Nicolas Papernot, Nicolas Papernot, 2017, ArXiv.

Markpainting: Adversarial Machine Learning meets Inpainting

Nicolas Papernot, Ross Anderson, Ilia Shumailov, 2021, ICML.

Adversarial examples for network intrusion detection systems

Nicolas Papernot, Ryan Sheatsley, P. Mcdaniel, 2022, J. Comput. Secur..

Architectural Backdoors in Neural Networks

Nicolas Papernot, R. Mullins, Ilia Shumailov, 2022, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning

Nicolas Papernot, Hengrui Jia, Ilia Shumailov, 2021, USENIX Security Symposium.

Proof-of-Learning: Definitions and Practice

Nicolas Papernot, Varun Chandrasekaran, Mohammad Yaghini, 2021, 2021 IEEE Symposium on Security and Privacy (SP).

Entangled Watermarks as a Defense against Model Extraction pdf

Nicolas Papernot, Hengrui Jia, Christopher A. Choquette-Choo, 2020, USENIX Security Symposium.

Sponge Examples: Energy-Latency Attacks on Neural Networks

Robert Mullins, Nicolas Papernot, Ross Anderson, 2020, 2021 IEEE European Symposium on Security and Privacy (EuroS&P).

Towards the Science of Security and Privacy in Machine Learning pdf

Michael P. Wellman, Patrick D. McDaniel, Nicolas Papernot, 2016, ArXiv.

Verifiable and Provably Secure Machine Unlearning

Nicolas Papernot, Varun Chandrasekaran, O. Ohrimenko, 2022, ArXiv.

The Privacy Onion Effect: Memorization is Relative

Florian Tramèr, Nicolas Papernot, Nicholas Carlini, 2022, NeurIPS.

Challenges towards the Next Frontier in Privacy

Ryan M. Rogers, Weijie J. Su, Nicolas Papernot, 2023, ArXiv.

What Does It Mean for Machine Learning to Be Trustworthy

Nicolas Papernot, Nicolas Papernot, 2020 .

Characterizing the Limits and Defenses of Machine Learning in Adversarial Settings

Nicolas Papernot, Nicolas Papernot, 2018 .

Machine Learning at Scale with Differential Privacy in TensorFlow

Nicolas Papernot, Nicolas Papernot, 2019 .

On the Limitations of Stochastic Pre-processing Defenses

Nicolas Papernot, Ilia Shumailov, Kassem Fawaz, 2022, NeurIPS.

SoK: Machine Learning Governance pdf

Nicolas Papernot, Varun Chandrasekaran, Mohammad Yaghini, 2021, ArXiv.

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

David Lie, Nicolas Papernot, Varun Chandrasekaran, 2021, ArXiv.

On Evaluating Adversarial Robustness pdf

Aleksander Madry, Wieland Brendel, Nicholas Carlini, 2019, ArXiv.

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

Úlfar Erlingsson, Nicolas Papernot, Nicholas Carlini, 2019, ArXiv.

Pipe Overflow: Smashing Voice Authentication for Fun and Profit

Nicolas Papernot, Ilia Shumailov, Kassem Fawaz, 2022, ArXiv.

Unrolling SGD: Understanding Factors Influencing Machine Unlearning

Nicolas Papernot, Varun Chandrasekaran, Gabriel Deza, 2021, 2022 IEEE 7th European Symposium on Security and Privacy (EuroS&P).

Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning pdf

Milad Nasr, Shuang Song, Abhradeep Thakurta, 2021, 2021 IEEE Symposium on Security and Privacy (SP).

Label-Only Membership Inference Attacks pdf

Nicolas Papernot, Florian Tramèr, Nicholas Carlini, 2020, ICML.

Increasing the Cost of Model Extraction with Calibrated Proof of Work

Nicolas Papernot, Adam Dziedzic, Muhammad Ahmad Kaleem, 2022, ICLR.

Machine Learning in Adversarial Settings

Patrick D. McDaniel, Z. Berkay Celik, Nicolas Papernot, 2016, IEEE Security & Privacy.

Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples pdf

Patrick D. McDaniel, Nicolas Papernot, Ian J. Goodfellow, 2016, ArXiv.

SoK: Security and Privacy in Machine Learning

Michael P. Wellman, Patrick D. McDaniel, Nicolas Papernot, 2018, 2018 IEEE European Symposium on Security and Privacy (EuroS&P).

Adversarial Examples for Malware Detection

Patrick D. McDaniel, Michael Backes, Nicolas Papernot, 2017, ESORICS.

A Marauder's Map of Security and Privacy in Machine Learning: An overview of current and future research directions for making machine learning secure and private

Nicolas Papernot, Nicolas Papernot, 2018, AISec@CCS.

Private Multi-Winner Voting for Machine Learning

Christopher A. Choquette-Choo, Nicolas Papernot, V. Suriyakumar, 2022, Proc. Priv. Enhancing Technol..

Scalable Private Learning with PATE pdf

Úlfar Erlingsson, Ilya Mironov, Shuang Song, 2018, ICLR.

Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data pdf

Martín Abadi, Úlfar Erlingsson, Kunal Talwar, 2016, ICLR.

On the Robustness of Cooperative Multi-Agent Reinforcement Learning

Alberto Leon-Garcia, Sai Qian Zhang, Nicolas Papernot, 2020, 2020 IEEE Security and Privacy Workshops (SPW).

Adversarial Perturbations Against Deep Neural Networks for Malware Classification pdf

Patrick D. McDaniel, Michael Backes, Nicolas Papernot, 2016, ArXiv.

Bounding Membership Inference

Nicolas Papernot, Ilia Shumailov, Franziska Boenisch, 2022, ArXiv.

A Zest of LIME: Towards Architecture-Independent Model Distances

Nicolas Papernot, Hengrui Jia, A. Shamsabadi, 2022, ICLR.

Hyperparameter Tuning with Renyi Differential Privacy

Nicolas Papernot, T. Steinke, 2021, ICLR.

Measuring Forgetting of Memorized Training Examples

Florian Tramèr, Nicolas Papernot, Nicholas Carlini, 2022, ICLR.

CaPC Learning: Confidential and Private Collaborative Learning pdf

Somesh Jha, Nicolas Papernot, Adam Dziedzic, 2021, ICLR.

When the Curious Abandon Honesty: Federated Learning Is Not Private

Nicolas Papernot, Ilia Shumailov, Adam Dziedzic, 2021, 2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P).

Is Federated Learning a Practical PET Yet?

Nicolas Papernot, Ilia Shumailov, Adam Dziedzic, 2023, ArXiv.

Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation

Nicolas Papernot, Ilia Shumailov, Adam Dziedzic, 2023, 2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P).

Data-Free Model Extraction pdf

Nicolas Papernot, Pratyush Maini, Jean-Baptiste Truong, 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

Patrick Traynor, Nicolas Papernot, Hadi Abdullah, 2020, 2021 IEEE Symposium on Security and Privacy (SP).

p-DkNN: Out-of-Distribution Detection Through Statistical Testing of Deep Representations

Murat A. Erdogdu, Nicolas Papernot, Adam Dziedzic, 2022, ArXiv.

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

Ankur P. Parikh, Mohit Iyyer, Nicolas Papernot, 2019, ICLR.

Rearchitecting Classification Frameworks For Increased Robustness

Nicolas Papernot, S. Jha, Varun Chandrasekaran, 2019, 1905.10900.

Differentially Private Speaker Anonymization

Nicolas Papernot, E. Vincent, B. M. L. Srivastava, 2022, Proc. Priv. Enhancing Technol..

On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping pdf

Tudor Dumitras, Nicolas Papernot, Yigitcan Kaya, 2020, ArXiv.

Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations pdf

Jorn-Henrik Jacobsen, Nicolas Papernot, Nicholas Carlini, 2020, ICML.

Cleverhans V0.1: an Adversarial Machine Learning Library pdf

Patrick D. McDaniel, Nicolas Papernot, Ian J. Goodfellow, 2016, ArXiv.

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

Nicolas Papernot, V. Betz, Andrew Boutros, 2020, 2020 International Conference on Field-Programmable Technology (ICFPT).

Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models

Nicolas Papernot, Adam Dziedzic, Franziska Boenisch, 2023, NeurIPS.

Have it your way: Individualized Privacy Assignment for DP-SGD

Nicolas Papernot, Adam Dziedzic, Franziska Boenisch, 2023, ArXiv.

Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning

Nicolas Papernot, M. Ghassemi, Karsten Roth, 2022, ICLR.

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

Nicolas Papernot, Ilia Shumailov, Jin Peng Zhou, 2020, ArXiv.

LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?

Nicolas Papernot, Y. Gal, V. Papyan, 2023, ArXiv.

The Curse of Recursion: Training on Generated Data Makes Models Forget

Nicolas Papernot, Y. Gal, Ilia Shumailov, 2023, ArXiv.

M EASURING F ORGETTING OF M EMORIZED T RAINING E XAMPLES

Florian Tramèr, Nicolas Papernot, Nicholas Carlini, 2023 .

M ODEL D EMENTIA : G ENERATED D ATA M AKES M ODELS F ORGET

Nicolas Papernot, Y. Gal, Ilia Shumailov, 2023 .

Interpretability in Safety-Critical FinancialTrading Systems pdf

Colin Rowat, Nicolas Papernot, Adelin Travers, 2021, ArXiv.

Security and Science of Agility

Ananthram Swami, Srikanth V. Krishnamurthy, Thomas F. La Porta, 2014, MTD '14.

Washing The Unwashable : On The (Im)possibility of Fairwashing Detection

Nicolas Papernot, S. Gambs, U. Aïvodji, 2022, NeurIPS.

Improving Differentially Private Models with Active Learning pdf

Sameer Singh, Neoklis Polyzotis, Nicolas Papernot, 2019, ArXiv.

The Adversarial Implications of Variable-Time Inference

Nicolas Papernot, Y. Elovici, J. Kotak, 2023, 2309.02159.

Pipe Overflow: Smashing Voice Authentication for Fun and Profit

Nicolas Papernot, Ilia Shumailov, Kassem Fawaz, 2022, ArXiv.

Training Private Models That Know What They Don't Know

Nicolas Papernot, Krishnamurthy Dvijotham, Abhradeep Thakurta, 2023, ArXiv.

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD

Nicolas Papernot, Hengrui Jia, Ilia Shumailov, 2023, ArXiv.

Selective Classification Via Neural Network Training Dynamics

Nicolas Papernot, Adam Dziedzic, Kimia Hamidieh, 2022, arXiv.org.

Tubes Among Us: Analog Attack on Automatic Speaker Identification

Nicolas Papernot, Ilia Shumailov, Kassem Fawaz, 2022, USENIX Security Symposium.

Machine Unlearning

Christopher A. Choquette-Choo, Nicolas Papernot, D. Lie, 2019, 2021 IEEE Symposium on Security and Privacy (SP).

On the Protection of Private Information in Machine Learning Systems: Two Recent Approches

Nicolas Papernot, H. B. McMahan, Martín Abadi, 2017, 2017 IEEE 30th Computer Security Foundations Symposium (CSF).

On the Privacy Risk of In-context Learning

Nicolas Papernot, Franziska Boenisch, Mohammad Yaghini, 2022 .

Dataset Inference for Self-Supervised Models

Nicolas Papernot, Adam Dziedzic, Muhammad Ahmad Kaleem, 2022, NeurIPS.

Proof-of-Learning: Definitions and Practice

Christopher A. Choquette-Choo, Nicolas Papernot, Varun Chandrasekaran, 2021, 2021 IEEE Symposium on Security and Privacy (SP).