Tu Trinh

2 papers · 2024–2025 · 2 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (2) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (6)

Conferences

ICLR (1) NIPS (1)

Top co-authors

Vaughn Robinson (1) Alexandra Souly (1) Saranya Vijayakumar (1) Summer Yue (1) Elaine Lau (1) Sean M. Hendryx (1) Elvis Hsieh (1) Matt Fredrikson (1) Pieter Abbeel (1) Zifan Wang (1)

Keywords

safety fine-tuning (1) attack success rate (1) harmfulness evaluation (1) jailbreak benchmark (1)

Papers

Aligned LLMs Are Not Aligned Browser Agents ICLR 2025

A StrongREJECT for Empty Jailbreaks NIPS 2024