Christopher A. Choquette-Choo

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Privacy Auditing of Large Language Models.

[BibT_eX]

[DOI]

Ashwinee Panda

Xinyu Tang

Prateek Mittal

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Scalable Extraction of Training Data from Aligned, Production Language Models.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD.

[BibT_eX]

[DOI]

Borja Balle

Jamie Hayes

Adam Smith

Andreas Terzis

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Near-Exact Privacy Amplification for Matrix Mechanisms.

[BibT_eX]

[DOI]

Saminul Haque

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Near-Optimal Rates for O(1)-Smooth DP-SCO with a Single Epoch and Large Batches.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Algorithmic Learning Theory, 2025

Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training.

[BibT_eX]

[DOI]

Jaydeep Borkar

Niloofar Mireshghallah

David A. Smith

Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice.

[BibT_eX]

[DOI]

CoRR, 2024

Gemma 2: Improving Open Language Models at a Practical Size.

[BibT_eX]

[DOI]

Hanna Klimczak-Plucinska

CoRR, 2024

CodeGemma: Open Code Models Based on Gemma.

[BibT_eX]

[DOI]

CoRR, 2024

Optimal Rates for DP-SCO with a Single Epoch and Large Batches.

[BibT_eX]

[DOI]

Abhradeep Thakurta

CoRR, 2024

Phantom: General Trigger Attacks on Retrieval Augmented Language Generation.

[BibT_eX]

[DOI]

Cristina Nita-Rotaru

Alina Oprea

CoRR, 2024

Gemma: Open Models Based on Gemini Research and Technology.

[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

Auditing Private Prediction.

[BibT_eX]

[DOI]

Karan Chadha

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

Teach LLMs to Phish: Stealing Private Information from Language Models.

[BibT_eX]

[DOI]

Ashwinee Panda

Zhengming Zhang

Yaoqing Yang

Prateek Mittal

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Privacy Amplification for Matrix Mechanisms.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning.

[BibT_eX]

[DOI]

Krishnamurthy Dj Dvijotham

Krishna Pillutla

Proceedings of the Twelfth International Conference on Learning Representations, 2024

User Inference Attacks on Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

2023

Private Multi-Winner Voting for Machine Learning.

[BibT_eX]

[DOI]

Adam Dziedzic

Natalie Dullerud

Vinith M. Suriyakumar

Ali Shahin Shamsabadi

Muhammad Ahmad Kaleem

Somesh Jha

Xiao Wang

Proc. Priv. Enhancing Technol., January, 2023

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

[BibT_eX]

[DOI]

Eric Wallace

CoRR, 2023

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

[BibT_eX]

[DOI]

CoRR, 2023

Robust and Actively Secure Serverless Collaborative Learning.

[BibT_eX]

[DOI]

Olive Franzese

Adam Dziedzic

Mark R. Thomas

Muhammad Ahmad Kaleem

CoRR, 2023

MADLAD-400: A Multilingual And Document-Level Large Audited Dataset.

[BibT_eX]

[DOI]

CoRR, 2023

Are aligned neural networks adversarially aligned?

[BibT_eX]

[DOI]

CoRR, 2023

(Amplified) Banded Matrix Factorization: A unified approach to private training.

[BibT_eX]

[DOI]

CoRR, 2023

PaLM 2 Technical Report.

[BibT_eX]

[DOI]

CoRR, 2023

Students Parrot Their Teachers: Membership Inference on Model Distillation.

[BibT_eX]

[DOI]

CoRR, 2023

Students Parrot Their Teachers: Membership Inference on Model Distillation.

[BibT_eX]

[DOI]

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

Robust and Actively Secure Serverless Collaborative Learning.

[BibT_eX]

[DOI]

Nicholas Franzese

Adam Dziedzic

Mark R. Thomas

Muhammad Ahmad Kaleem

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

(Amplified) Banded Matrix Factorization: A unified approach to private training.

[BibT_eX]

[DOI]

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

Private Federated Learning with Autotuned Compression.

[BibT_eX]

[DOI]

Enayat Ullah

Peter Kairouz

Sewoong Oh

Proceedings of the International Conference on Machine Learning, 2023

Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning.

[BibT_eX]

[DOI]

Hugh Brendan McMahan

J. Keith Rush

Proceedings of the International Conference on Machine Learning, 2023

Proof-of-Learning is Currently More Broken Than You Think.

[BibT_eX]

[DOI]

Natalie Dullerud

Proceedings of the 8th IEEE European Symposium on Security and Privacy, 2023

Federated Learning of Gboard Language Models with Differential Privacy.

[BibT_eX]

[DOI]

Yanxiang Zhang

Galen Andrew

Proceedings of the The 61st Annual Meeting of the Association for Computational Linguistics: Industry Track, 2023

2022

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

[BibT_eX]

[DOI]

CoRR, 2022

Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Search.

[BibT_eX]

[DOI]

Yannis Cattan

Abhradeep Thakurta

CoRR, 2022

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

[BibT_eX]

[DOI]

Natalie Dullerud

CoRR, 2022

The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning.

[BibT_eX]

[DOI]

Wei-Ning Chen

Peter Kairouz

Ananda Theertha Suresh

Proceedings of the International Conference on Machine Learning, 2022

2021

Entangled Watermarks as a Defense against Model Extraction.

[BibT_eX]

[DOI]

Hengrui Jia

Proceedings of the 30th USENIX Security Symposium, 2021

Proof-of-Learning: Definitions and Practice.

[BibT_eX]

[DOI]

Hengrui Jia

Mohammad Yaghini

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

Machine Unlearning.

[BibT_eX]

[DOI]

Lucas Bourtoule

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

Label-Only Membership Inference Attacks.

[BibT_eX]

[DOI]

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

CaPC Learning: Confidential and Private Collaborative Learning.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Entangled Watermarks as a Defense against Model Extraction.

[BibT_eX]

[DOI]

Hengrui Jia

CoRR, 2020

2019

A Multi-label, Dual-Output Deep Neural Network for Automated Bug Triaging.

[BibT_eX]

[DOI]