Xiangyu Qi

Venues

Frequent coauthors

Papers

1. Defensive Prompt Patch: A Robust and Generalizable Defense of Large Language Models against Jailbreak Attacks
   ACL 2025 ·

   Chen Xiong

   DBLP profile ↗ORCID search ↗
2. Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability
   NAACL 2025 ·

   Haonan Li

   DBLP profile ↗ORCID search ↗
3. On Evaluating the Durability of Safeguards for Open-Weight LLMs
   ICLR 2025 · Xiangyu Qi
4. SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
   ICLR 2025 ·

   Tinghao Xie

   DBLP profile ↗ORCID search ↗
5. Safety Alignment Should be Made More Than Just a Few Tokens Deep
   ICLR 2025 · Xiangyu Qi
6. Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
   ICML 2024 ·

   Boyi Wei

   DBLP profile ↗ORCID search ↗
7. BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
   ICLR 2024 ·

   Tinghao Xie

   DBLP profile ↗ORCID search ↗
8. BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
   NeurIPS 2024 ·

   Jiongxiao Wang

   DBLP profile ↗ORCID search ↗
9. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
   ICLR 2024 · Xiangyu Qi
10. Visual Adversarial Examples Jailbreak Aligned Large Language Models
    AAAI 2024 · Xiangyu Qi