Christopher A. Choquette-Choo

发表

Label-Only Membership Inference Attacks pdf

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

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

David Sheldon, Jonny Proppe, Christopher A. Choquette-Choo, 2019, 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA).

Entangled Watermarks as a Defense against Model Extraction pdf

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

CaPC Learning: Confidential and Private Collaborative Learning pdf

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

Entangled Watermarks as a Defense against Model Extraction pdf

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

Label-Only Membership Inference Attacks

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

Proof-of-Learning: Definitions and Practice

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

CaPC Learning: Confidential and Private Collaborative Learning pdf

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

Machine Unlearning pdf

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

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

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

Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Search

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

Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning

Christopher A. Choquette-Choo, H. B. McMahan, Abhradeep Thakurta, 2022, 2211.06530.

Poisoning Web-Scale Training Datasets is Practical

Christopher A. Choquette-Choo, Florian Tramèr, Nicholas Carlini, 2023, ArXiv.

Students Parrot Their Teachers: Membership Inference on Model Distillation

Christopher A. Choquette-Choo, Nicholas Carlini, Katherine Lee, 2023, ArXiv.

Private Multi-Winner Voting for Machine Learning

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

PaLM 2 Technical Report

Andrew M. Dai, Jan A. Botha, Laurent El Shafey, 2023, ArXiv.

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

Christopher A. Choquette-Choo, Florian Tramèr, Nicholas Carlini, 2022, ArXiv.

Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning

Christopher A. Choquette-Choo, H. B. McMahan, Abhradeep Thakurta, 2022, ICML.

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

Christopher A. Choquette-Choo, Florian Tramèr, Nicholas Carlini, 2022, ArXiv.

Federated Learning of Gboard Language Models with Differential Privacy

Christopher A. Choquette-Choo, H. B. McMahan, P. Kairouz, 2023, ArXiv.

Are aligned neural networks adversarially aligned?

Pang Wei Koh, Christopher A. Choquette-Choo, Florian Tramèr, 2023, NeurIPS.

The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning

Christopher A. Choquette-Choo, A. Suresh, P. Kairouz, 2022, ICML.

Federated Learning of Gboard Language Models with Differential Privacy

Christopher A. Choquette-Choo, H. B. McMahan, P. Kairouz, 2023, ACL.

PaLM 2 Technical Report

Andrew M. Dai, Jan A. Botha, Laurent El Shafey, 2023, ArXiv.

Machine Unlearning

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

User Inference Attacks on Large Language Models

Christopher A. Choquette-Choo, P. Kairouz, Nikhil Kandpal, 2023, ArXiv.

Privacy Side Channels in Machine Learning Systems

Christopher A. Choquette-Choo, Florian Tramèr, Nicholas Carlini, 2023, USENIX Security Symposium.

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

Christopher A. Choquette-Choo, Orhan Firat, Aditya Kusupati, 2023, ArXiv.

Gemini: A Family of Highly Capable Multimodal Models

Tara N. Sainath, Dalia El Badawy, Reinald Kim Amplayo, 2023, ArXiv.

PaLM 2 Technical Report

Andrew M. Dai, Jan A. Botha, Laurent El Shafey, 2023, ArXiv.

Scalable Extraction of Training Data from (Production) Language Models

Christopher A. Choquette-Choo, Florian Tramèr, Nicholas Carlini, 2023, ArXiv.

Private Federated Learning with Autotuned Compression

Christopher A. Choquette-Choo, Sewoong Oh, P. Kairouz, 2023, ICML.

Proof-of-Learning: Definitions and Practice

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

Gemini: A Family of Highly Capable Multimodal Models

Tara N. Sainath, Dalia El Badawy, Reinald Kim Amplayo, 2023, ArXiv.

Gemma: Open Models Based on Gemini Research and Technology

Pier Giuseppe Sessa, Charline Le Lan, Christopher A. Choquette-Choo, 2024, ArXiv.

Zero-shot sampling of adversarial entities in biomedical question answering

Christopher A. Choquette-Choo, Daniel M. Ziegler, Alec Radford, 2024, 2402.10527.

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Dalia El Badawy, Nicola De Cao, Charline Le Lan, 2024, ArXiv.

Communication Efﬁcient Federated Learning with Secure Aggregation and Differential Privacy

Christopher A. Choquette-Choo, Phillip B. Gibbons, Ameet S. Talwalkar, 2021 .

Report of the 1st Workshop on Generative AI and Law

Christopher A. Choquette-Choo, Swee Leng Harris, Nicholas Carlini, 2023, SSRN Electronic Journal.