AI safety researcher

Matthew Jagielski

Google Scholar dblp ORCID

Last 12 months7 papers

Evaluation and benchmarks 2Other 1Defenses 1

AI safety papers from the last year

On this site: 59 papers

September 2026

Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks
Sep 14arXiv ↗

August 2026

The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark
Aug 11Evaluation and benchmarksarXiv ↗

July 2026

CryptanalysisBench: Can LLMs do Cryptanalysis?
Jul 20Evaluation and benchmarksarXiv ↗
The 2026 Singapore Consensus on Global AI Safety Research Priorities
Jul 9OtherarXiv ↗
Untrusted Content Masking for Web Agents with Security Guarantees
Jul 6DefensesarXiv ↗

February 2026

Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning
Feb 28arXiv ↗

January 2026

Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models
Jan 27arXiv ↗

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