PPaperPicks

Xiangyu Qi

10 papers at tracked venues · 9 at CORE A* · active 2024–2025

DBLP profile ↗ORCID search ↗

Venues

ICLR ×5AAAI ×1ACL ×1ICML ×1NAACL ×1NeurIPS ×1

Frequent coauthors

Prateek Mittal
×7
Peter Henderson
×6
Tinghao Xie
×5
Boyi Wei
×3
Yangsibo Huang
×3
Kaixuan Huang
×3
Pin-Yu Chen
×2
Luxi He
×2
Yi Zeng
×2
Ruoxi Jia
×2
Bo Li
×2
Ashwinee Panda
×2

Papers

  1. Defensive Prompt Patch: A Robust and Generalizable Defense of Large Language Models against Jailbreak Attacks
    ACL 2025 ·
    Chen Xiong
    , Xiangyu Qi,
    Pin-Yu Chen
    ,
    Tsung-Yi Ho
  2. Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability
    NAACL 2025 ·
    Haonan Li
    ,
    Xudong Han
    ,
    Zenan Zhai
    ,
    Honglin Mu
    ,
    Hao Wang
    ,
    Zhenxuan Zhang
    ,
    Yilin Geng
    ,
    Shom Lin
    ,
    Renxi Wang
    ,
    Artem Shelmanov
    , Xiangyu Qi,
    Yuxia Wang
    ,
    Donghai Hong
    ,
    Youliang Yuan
    ,
    Meng Chen
    ,
    Haoqin Tu
    ,
    Fajri Koto
    ,
    Cong Zeng
    ,
    Tatsuki Kuribayashi
    ,
    Rishabh Bhardwaj
    ,
    Bingchen Zhao
    ,
    Yawen Duan
    ,
    Yi Liu
    ,
    Emad A. Alghamdi
    ,
    Yaodong Yang
    ,
    Yinpeng Dong
    ,
    Soujanya Poria
    ,
    Pengfei Liu
    ,
    Zhengzhong Liu
    ,
    Xuguang Ren
    ,
    Eduard H. Hovy
    ,
    Iryna Gurevych
    ,
    Preslav Nakov
    ,
    Monojit Choudhury
    ,
    Timothy Baldwin
  3. On Evaluating the Durability of Safeguards for Open-Weight LLMs
    ICLR 2025 · Xiangyu Qi,
    Boyi Wei
    ,
    Nicholas Carlini
    ,
    Yangsibo Huang
    ,
    Tinghao Xie
    ,
    Luxi He
    ,
    Matthew Jagielski
    ,
    Milad Nasr
    ,
    Prateek Mittal
    ,
    Peter Henderson
  4. SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
    ICLR 2025 ·
    Tinghao Xie
    , Xiangyu Qi,
    Yi Zeng
    ,
    Yangsibo Huang
    ,
    Udari Madhushani Sehwag
    ,
    Kaixuan Huang
    ,
    Luxi He
    ,
    Boyi Wei
    ,
    Dacheng Li
    ,
    Ying Sheng
    ,
    Ruoxi Jia
    ,
    Bo Li
    ,
    Kai Li
    ,
    Danqi Chen
    ,
    Peter Henderson
    ,
    Prateek Mittal
  5. Safety Alignment Should be Made More Than Just a Few Tokens Deep
    ICLR 2025 · Xiangyu Qi,
    Ashwinee Panda
    ,
    Kaifeng Lyu
    ,
    Xiao Ma
    ,
    Subhrajit Roy
    ,
    Ahmad Beirami
    ,
    Prateek Mittal
    ,
    Peter Henderson
  6. Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
    ICML 2024 ·
    Boyi Wei
    ,
    Kaixuan Huang
    ,
    Yangsibo Huang
    ,
    Tinghao Xie
    , Xiangyu Qi,
    Mengzhou Xia
    ,
    Prateek Mittal
    ,
    Mengdi Wang
    ,
    Peter Henderson
  7. BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
    ICLR 2024 ·
    Tinghao Xie
    , Xiangyu Qi,
    Ping He
    ,
    Yiming Li
    ,
    Jiachen T. Wang
    ,
    Prateek Mittal
  8. BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
    NeurIPS 2024 ·
    Jiongxiao Wang
    ,
    Jiazhao Li
    ,
    Yiquan Li
    , Xiangyu Qi,
    Junjie Hu
    ,
    Sharon Li
    ,
    Patrick McDaniel
    ,
    Muhao Chen
    ,
    Bo Li
    ,
    Chaowei Xiao
  9. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
    ICLR 2024 · Xiangyu Qi,
    Yi Zeng
    ,
    Tinghao Xie
    ,
    Pin-Yu Chen
    ,
    Ruoxi Jia
    ,
    Prateek Mittal
    ,
    Peter Henderson
  10. Visual Adversarial Examples Jailbreak Aligned Large Language Models
    AAAI 2024 · Xiangyu Qi,
    Kaixuan Huang
    ,
    Ashwinee Panda
    ,
    Peter Henderson
    ,
    Mengdi Wang
    ,
    Prateek Mittal