AI safety researcher

Somesh Jha

University of Wisconsin-Madison

Google Scholar dblp OpenReview ORCID Homepage

Last 12 months13 papers

Defenses 1Other 1

AI safety papers from the last year

On this site: 84 papers

October 2026

Secure-CUA: Controlling Untrusted Influence in Computer-Use Agents
Oct 7DefensesarXiv ↗

September 2026

Beyond Predictable Paths: Redefining AI Security Incident Reporting for Agents
Sep 21OtherarXiv ↗
Differentially Private Paired Table-Image Multimodal Synthesis
Sep 1arXiv ↗

June 2026

May 2026

April 2026

PolicyBank: Evolving Policy Understanding for LLM Agents
Apr 16arXiv ↗

February 2026

Formal Policy Enforcement for Agentic Systems
Feb 18arXiv ↗

December 2025

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