AI safety researcher

Edward Suh

Google Scholar dblp

Last 12 months2 papers

Defenses 1

AI safety papers from the last year

On this site: 6 papers

September 2026

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents
Sep 5DefensesarXiv ↗

November 2025

Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis
Nov 30arXiv ↗

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