Christopher A. Choquette-Choo

Google (United States) — United States

Computer Science · Physical Sciences

16h-index2.7kcitations57works31.22yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Privacy-Preserving Technologies in Data(22), Adversarial Robustness in Machine Learning(14), Topic Modeling(11), Cryptography and Data Security(11), Stochastic Gradient Optimization Techniques(8)

Publications55 total

Extracting alignment data in open models
arXiv (Cornell University)·2025Open Access
VaultGemma: A Differentially Private Gemma Model
arXiv (Cornell University)·2025Open Access
Correlated Noise Mechanisms for Differentially Private Learning
arXiv (Cornell University)·2025Open Access
Exploring the limits of strong membership inference attacks on large language models
ArXiv.org·2025Open Access
Lessons from Defending Gemini Against Indirect Prompt Injections
arXiv (Cornell University)·2025Open Access
LLMs unlock new paths to monetizing exploits
arXiv (Cornell University)·2025Open Access
Scaling Laws for Differentially Private Language Models
arXiv (Cornell University)·2025Open Access
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
SSRN Electronic Journal·2025Open Access
Measuring memorization in language models via probabilistic extraction
2025· 5 citedOpen Access
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice
SSRN Electronic Journal·2025· 5 citedOpen Access
Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
2025· 1 citedOpen Access
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
arXiv (Cornell University)·2024Open Access
Near Exact Privacy Amplification for Matrix Mechanisms
arXiv (Cornell University)·2024Open Access
The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
arXiv (Cornell University)·2024· 1 citedOpen Access
Gemma 2: Improving Open Language Models at a Practical Size
arXiv (Cornell University)·2024· 125 citedOpen Access
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
arXiv (Cornell University)·2024Open Access
Optimal Rates for $O(1)$-Smooth DP-SCO with a Single Epoch and Large Batches
arXiv (Cornell University)·2024Open Access
Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation
arXiv (Cornell University)·2024· 3 citedOpen Access
Poisoning Web-Scale Training Datasets is Practical
2024· 75 cited
Gemma: Open Models Based on Gemini Research and Technology
arXiv (Cornell University)·2024· 217 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Nicolas Papernot(18), Matthew Jagielski(16), Katherine Lee(15), Milad Nasr(12), Nicholas Carlini(10), Varun Chandrasekaran(9), Hengrui Jia(9), Florian Tramèr(8), A. Feder Cooper(8), Daphne Ippolito(7), Andreas Terzis(7), Natalie Dullerud(7), Ilia Shumailov(7), Niloofar Mireshghallah(7), Abhradeep Thakurta(6), Adam Dziedzic(5), Jamie Hayes(5), James Grimmelmann(5), Christopher De(5), Mark A. Lemley(5)