conftrace_
← Authors

Patrick McDaniel

5 papers · 2018–2025 · 3 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+2 more ↓ 🏃 Academic Marathon (7) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (3) 🌉 Interdisciplinary Bridge
🚀 Conference Pioneer ❓ The Questioner

Conferences

ICLR (3) ICCV (1) NIPS (1)

Top co-authors

Chaowei Xiao (3) Bo Li (3) Xiaogeng Liu (2) Somesh Jha (2) Alexey Kurakin (1) Eric Pauley (1) Dan Boneh (1) Yixuan Li (1) Ryan Sheatsley (1) Kunyang Li (1)

Keywords

adversarial robustness (1) safety alignment (1) fine-tuning attack (1) jailbreak defense (1) backdoor trigger (1) prefixed safety (1)

Papers

On the Robustness Tradeoff in Fine-Tuning ICCV 2025 Can Watermarks be Used to Detect LLM IP Infringement For Free? ICLR 2025 AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs ICLR 2025 BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment NIPS 2024 Ensemble Adversarial Training: Attacks and Defenses ICLR 2018