Nicholas Carlini

Francisco Rodríguez-Henríquez

Jorge Chávez-Saab

Anna Hambitzer

Adi Shamir

IACR Cryptol. ePrint Arch., 2024

Stealing User Prompts from Mixture of Experts.

[BibT_eX]

[DOI]

CoRR, 2024

Remote Timing Attacks on Efficient Language Model Inference.

[BibT_eX]

[DOI]

CoRR, 2024

Persistent Pre-Training Poisoning of LLMs.

[BibT_eX]

[DOI]

CoRR, 2024

Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI.

[BibT_eX]

[DOI]

CoRR, 2024

Cutting through buggy adversarial example defenses: fixing 1 line of code breaks Sabre.

[BibT_eX]

[DOI]

CoRR, 2024

Forcing Diffuse Distributions out of Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models.

[BibT_eX]

[DOI]

CoRR, 2024

Diffusion Denoising as a Certified Defense against Clean-label Poisoning.

[BibT_eX]

[DOI]

Sanghyun Hong

Alexey Kurakin

CoRR, 2024

Query-Based Adversarial Prompt Generation.

[BibT_eX]

[DOI]

CoRR, 2024

Privacy Side Channels in Machine Learning Systems.

[BibT_eX]

[DOI]

Edoardo Debenedetti

Giorgio Severi

Proceedings of the 33rd USENIX Security Symposium, 2024

Poisoning Web-Scale Training Datasets is Practical.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2024

Evading Black-box Classifiers Without Breaking Eggs.

[BibT_eX]

[DOI]

Edoardo Debenedetti

Proceedings of the IEEE Conference on Secure and Trustworthy Machine Learning, 2024

Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining.

[BibT_eX]

[DOI]

Gautam Kamath

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Stealing part of a production language model.

[BibT_eX]

[DOI]

Krishnamurthy Dj Dvijotham

Daniel Paleka

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Initialization Matters for Adversarial Transfer Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Identifying and Mitigating the Security Risks of Generative AI.

[BibT_eX]

[DOI]

Found. Trends Priv. Secur., 2023

Scalable Extraction of Training Data from (Production) Language Models.

[BibT_eX]

[DOI]

Eric Wallace

Katherine Lee

CoRR, 2023

Report of the 1st Workshop on Generative AI and Law.

[BibT_eX]

[DOI]

CoRR, 2023

Identifying and Mitigating the Security Risks of Generative AI.

[BibT_eX]

[DOI]

CoRR, 2023

A LLM Assisted Exploitation of AI-Guardian.

[BibT_eX]

[DOI]

CoRR, 2023

Backdoor Attacks for In-Context Learning with Language Models.

[BibT_eX]

[DOI]

CoRR, 2023

Are aligned neural networks adversarially aligned?

[BibT_eX]

[DOI]

CoRR, 2023

Students Parrot Their Teachers: Membership Inference on Model Distillation.

[BibT_eX]

[DOI]

Katherine Lee

CoRR, 2023

Randomness in ML Defenses Helps Persistent Attackers and Hinders Evaluators.

[BibT_eX]

[DOI]

CoRR, 2023

Tight Auditing of Differentially Private Machine Learning.

[BibT_eX]

[DOI]

Proceedings of the 32nd USENIX Security Symposium, 2023

Extracting Training Data from Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the 32nd USENIX Security Symposium, 2023

Publishing Efficient On-device Models Increases Adversarial Vulnerability.

[BibT_eX]

[DOI]

Sanghyun Hong

Alexey Kurakin

Proceedings of the 2023 IEEE Conference on Secure and Trustworthy Machine Learning, 2023

Counterfactual Memorization in Neural Language Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Effective Robustness against Natural Distribution Shifts for Models with Different Training Data.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Students Parrot Their Teachers: Membership Inference on Model Distillation.

[BibT_eX]

[DOI]

Katherine Lee

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Are aligned neural networks adversarially aligned?

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Preventing Generation of Verbatim Memorization in Language Models Gives a False Sense of Privacy.

[BibT_eX]

[DOI]

Proceedings of the 16th International Natural Language Generation Conference, 2023

Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System.

[BibT_eX]

[DOI]

Proceedings of the 16th International Natural Language Generation Conference, 2023

Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems.

[BibT_eX]

[DOI]

Chawin Sitawarin

Proceedings of the International Conference on Machine Learning, 2023

Part-Based Models Improve Adversarial Robustness.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Measuring Forgetting of Memorized Training Examples.

[BibT_eX]

[DOI]

Abhradeep Guha Thakurta

Nicolas Papernot

Chiyuan Zhang

Proceedings of the Eleventh International Conference on Learning Representations, 2023

(Certified!!) Adversarial Robustness for Free!

[BibT_eX]

[DOI]

Krishnamurthy (Dj) Dvijotham

Leslie Rice

Mingjie Sun

J. Zico Kolter

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Quantifying Memorization Across Neural Language Models.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Security of Machine Learning (Dagstuhl Seminar 22281).

[BibT_eX]

[DOI]

Antonio Emanuele Cinà

Dagstuhl Reports, July, 2022

Considerations for Differentially Private Learning with Large-Scale Public Pretraining.

[BibT_eX]

[DOI]

Gautam Kamath

CoRR, 2022

Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy.

[BibT_eX]

[DOI]

CoRR, 2022

No Free Lunch in "Privacy for Free: How does Dataset Condensation Help Privacy".

[BibT_eX]

[DOI]

Vitaly Feldman

CoRR, 2022

(Certified!!) Adversarial Robustness for Free!

[BibT_eX]

[DOI]

Krishnamurthy Dvijotham

J. Zico Kolter

CoRR, 2022

Debugging Differential Privacy: A Case Study for Privacy Auditing.

[BibT_eX]

[DOI]

CoRR, 2022

Membership Inference Attacks From First Principles.

[BibT_eX]

[DOI]

Proceedings of the 43rd IEEE Symposium on Security and Privacy, 2022

Increasing Confidence in Adversarial Robustness Evaluations.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

The Privacy Onion Effect: Memorization is Relative.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Handcrafted Backdoors in Deep Neural Networks.

[BibT_eX]

[DOI]

Sanghyun Hong

Alexey Kurakin

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Data Poisoning Won't Save You From Facial Recognition.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Poisoning and Backdooring Contrastive Learning.

[BibT_eX]

[DOI]

Andreas Terzis

Proceedings of the Tenth International Conference on Learning Representations, 2022

Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets.

[BibT_eX]

[DOI]

Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, 2022

Deduplicating Training Data Makes Language Models Better.

[BibT_eX]

[DOI]

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

2021

Unsolved Problems in ML Safety.

[BibT_eX]

[DOI]

CoRR, 2021

NeuraCrypt is not private.

[BibT_eX]

[DOI]

CoRR, 2021

Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples.

[BibT_eX]

[DOI]

CoRR, 2021

Extracting Training Data from Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the 30th USENIX Security Symposium, 2021

Poisoning the Unlabeled Dataset of Semi-Supervised Learning.

[BibT_eX]

[DOI]

Proceedings of the 30th USENIX Security Symposium, 2021

Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning.

[BibT_eX]

[DOI]

Proceedings of the 42nd IEEE Symposium on Security and Privacy, 2021

Is Private Learning Possible with Instance Encoding?

[BibT_eX]

[DOI]

Proceedings of the 42nd IEEE Symposium on Security and Privacy, 2021

How Private is Machine Learning?

[BibT_eX]

[DOI]

Proceedings of the IH&MMSec '21: ACM Workshop on Information Hiding and Multimedia Security, 2021

Label-Only Membership Inference Attacks.

[BibT_eX]

[DOI]

Nicolas Papernot

Proceedings of the 38th International Conference on Machine Learning, 2021

Session details: Session 2A: Machine Learning for Cybersecurity.

[BibT_eX]

[DOI]

Proceedings of the AISec@CCS 2021: Proceedings of the 14th ACM Workshop on Artificial Intelligence and Security, 2021

Session details: Session 1: Adversarial Machine Learning.

[BibT_eX]

[DOI]

Proceedings of the AISec@CCS 2021: Proceedings of the 14th ACM Workshop on Artificial Intelligence and Security, 2021

2020

An Attack on InstaHide: Is Private Learning Possible with Instance Encoding?

[BibT_eX]

[DOI]

CoRR, 2020

Erratum Concerning the Obfuscated Gradients Attack on Stochastic Activation Pruning.

[BibT_eX]

[DOI]

Guneet S. Dhillon

CoRR, 2020

A Partial Break of the Honeypots Defense to Catch Adversarial Attacks.

[BibT_eX]

[DOI]

CoRR, 2020

High Accuracy and High Fidelity Extraction of Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 29th USENIX Security Symposium, 2020

On Adaptive Attacks to Adversarial Example Defenses.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Measuring Robustness to Natural Distribution Shifts in Image Classification.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Evading Deepfake-Image Detectors with White- and Black-Box Attacks.

[BibT_eX]

[DOI]

Hany Farid

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Cryptanalytic Extraction of Neural Network Models.

[BibT_eX]

[DOI]

Ilya Mironov

Proceedings of the Advances in Cryptology - CRYPTO 2020, 2020

AISec'20: 13th Workshop on Artificial Intelligence and Security.

[BibT_eX]

[DOI]

Sadia Afroz

Ambra Demontis

Proceedings of the CCS '20: 2020 ACM SIGSAC Conference on Computer and Communications Security, 2020

2019

ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring.

[BibT_eX]

[DOI]

CoRR, 2019

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

[BibT_eX]

[DOI]

Úlfar Erlingsson

Nicolas Papernot

CoRR, 2019

High-Fidelity Extraction of Neural Network Models.

[BibT_eX]

[DOI]

CoRR, 2019

Stateful Detection of Black-Box Adversarial Attacks.

[BibT_eX]

[DOI]

Steven Chen

CoRR, 2019

A critique of the DeepSec Platform for Security Analysis of Deep Learning Models.

[BibT_eX]

[DOI]

Dimitris S. Papailiopoulos

CoRR, 2019

SysML: The New Frontier of Machine Learning Systems.

[BibT_eX]

[DOI]

Alexandros G. Dimakis

Anastasios Kyrillidis

Shivaram Venkataraman

CoRR, 2019

Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness.

[BibT_eX]

[DOI]

CoRR, 2019

On Evaluating Adversarial Robustness.

[BibT_eX]

[DOI]

CoRR, 2019

Is AmI (Attacks Meet Interpretability) Robust to Adversarial Examples?

[BibT_eX]

[DOI]

CoRR, 2019

The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 28th USENIX Security Symposium, 2019

MixMatch: A Holistic Approach to Semi-Supervised Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Adversarial Examples Are a Natural Consequence of Test Error in Noise.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

AISec'19: 12th ACM Workshop on Artificial Intelligence and Security.

[BibT_eX]

[DOI]

Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, 2019

2018

Evaluation and Design of Robust Neural Network Defenses.

[BibT_eX]

[DOI]

PhD thesis, 2018

Unrestricted Adversarial Examples.

[BibT_eX]

[DOI]

CoRR, 2018

On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses.

[BibT_eX]

[DOI]

Anish Athalye

CoRR, 2018

The Secret Sharer: Measuring Unintended Neural Network Memorization & Extracting Secrets.

[BibT_eX]

[DOI]

CoRR, 2018

Audio Adversarial Examples: Targeted Attacks on Speech-to-Text.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Security and Privacy Workshops, 2018

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples.

[BibT_eX]

[DOI]

Anish Athalye

Proceedings of the 35th International Conference on Machine Learning, 2018

2017

MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples.

[BibT_eX]

[DOI]

CoRR, 2017

Ground-Truth Adversarial Examples.

[BibT_eX]

[DOI]

CoRR, 2017

Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong.

[BibT_eX]

[DOI]

CoRR, 2017

Adversarial Example Defense: Ensembles of Weak Defenses are not Strong.

[BibT_eX]

[DOI]

Proceedings of the 11th USENIX Workshop on Offensive Technologies, 2017

Towards Evaluating the Robustness of Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE Symposium on Security and Privacy, 2017

Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods.

[BibT_eX]

[DOI]

Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, 2017

2016

Defensive Distillation is Not Robust to Adversarial Examples.

[BibT_eX]

[DOI]

CoRR, 2016

Hidden Voice Commands.

[BibT_eX]

[DOI]

Proceedings of the 25th USENIX Security Symposium, 2016

2015

Control-Flow Bending: On the Effectiveness of Control-Flow Integrity.

[BibT_eX]

[DOI]

Proceedings of the 24th USENIX Security Symposium, 2015

2014

ROP is Still Dangerous: Breaking Modern Defenses.

[BibT_eX]

[DOI]

Proceedings of the 23rd USENIX Security Symposium, San Diego, CA, USA, August 20-22, 2014., 2014

2013

Improved Support for Machine-assisted Ballot-level Audits.

[BibT_eX]

[DOI]

Proceedings of the 2013 Electronic Voting Technology Workshop / Workshop on Trustworthy Elections, 2013

2012

Operator-Assisted Tabulation of Optical Scan Ballots.

[BibT_eX]

[DOI]

Proceedings of the 2012 Electronic Voting Technology Workshop / Workshop on Trustworthy Elections, 2012

An Evaluation of the Google Chrome Extension Security Architecture.

[BibT_eX]

[DOI]

Adrienne Porter Felt