conftrace_

Tanqiu Jiang

4 papers · 2020–2026 · 2 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓

🏃 Academic Marathon (5)

Conferences

ICLR (3) ACL (1)

Top co-authors

Ting Wang (3) Changjiang Li (2) Jiacheng Liang (2) Yuhui Wang (2) Fenglong Ma (2) Rongyi Zhu (1) Zian Wang (1) Yi Li (1) David P. Woodruff (1) Yisong Ruan (1)

Keywords

jailbreak attack (1) large reasoning model (1) safety reasoning (1) execution simulation (1)

Papers

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models ACL 2026 RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction ICLR 2025 RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models ICLR 2025 Learning-Augmented Data Stream Algorithms ICLR 2020