AI safety researcher

Seyed Hamed Hassani

University of Pennsylvania

Google Scholar dblp OpenReview ORCID Homepage

Last 12 months6 papers

Defenses 2

AI safety papers from the last year

On this site: 37 papers

May 2026

Stateful Online Monitoring Catches Distributed Agent Attacks
May 29DefensesarXiv ↗
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
May 12arXiv ↗

April 2026

Detecting Safety Violations Across Many Agent Traces
Apr 13DefensesarXiv ↗

February 2026

December 2025

MultiRisk: Multiple Risk Control via Iterative Score Thresholding
Dec 31arXiv ↗

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