AI safety researcher

Radha Poovendran

University of Washington

Google Scholar dblp ORCID Homepage

Last 12 months4 papers

Attacks 1Risky behavior 1

AI safety papers from the last year

On this site: 26 papers

October 2026

RSI Arena: Towards Recursive Self-Improvement with Human Feedback
Oct 24arXiv ↗
TAPDreamer: Transferable Adversarial Patches for World Action Models
Oct 5AttacksarXiv ↗

September 2026

Reward Hacking Challenges Oversight of Autonomous Research Agents
Sep 23Risky behaviorarXiv ↗

June 2026

CyberChainBench: Can AI Agents Secure Smart Contracts Against Real-World On-Chain Vulnerabilities?
Jun 24arXiv ↗

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