AI safety researcher

Matt Fredrikson

Google Scholar dblp OpenReview ORCID

Last 12 months8 papers

Evaluation and benchmarks 1

AI safety papers from the last year

On this site: 37 papers

June 2026

Steal the Patch Size: Adversarially Manipulate Vision-Language Models
Jun 30arXiv ↗

May 2026

A New Framework for Cybersecurity Refusals in AI Agents
May 31arXiv ↗

March 2026

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
Mar 16Evaluation and benchmarksarXiv ↗

February 2026

December 2025

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.