Matthew Jagielski

Black-Box Privacy Attacks on Shared Representations in Multitask Learning

Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning

Exploiting Reasoning Patterns in Language Models for Indirect Targeted Poisoning

Should We Forget About Certified Unlearning? Evaluating the Pitfalls of Noisy Methods

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On

Exploring the limits of strong membership inference attacks on large language models

Scalable Extraction of Training Data from Aligned, Production Language Models

On Evaluating the Durability of Safeguards for Open-Weight LLMs

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards

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

Phantom: General Trigger Attacks on Retrieval Augmented Language Generation