PPaperPicks

Xinlei He

18 papers at tracked venues · 16 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

AAAI ×3S&P ×3USENIX Security ×3ACL ×2EMNLP ×2SIGKDD ×2CCS ×1NDSS ×1NeurIPS ×1

Frequent coauthors

Zhen Sun
×8
Yule Liu
×6
Yang Zhang
×6
Tianshuo Cong
×6
Jingyi Zheng
×5
Zongmin Zhang
×4
Michael Backes
×3
Jihui Guo
×2
Xinyue Shen
×2
Ziyi Zhang
×2
Qi Li
×2
Tianyi Hu
×2

Papers

  1. 6DAttack: Backdoor Attacks in the 6DoF Pose Estimation
    AAAI 2026 ·
    Jihui Guo
    ,
    Zongmin Zhang
    ,
    Zhen Sun
    ,
    Yuhao Yang
    ,
    Jinlin Wu
    ,
    Fu Zhang
    , Xinlei He
  2. An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses
    AAAI 2026 ·
    Hao Liang
    ,
    Wanrong Zhang
    , Xinlei He,
    Kaishun Wu
    ,
    Hong Xing
  3. Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media
    ACL 2025 ·
    Zhen Sun
    ,
    Zongmin Zhang
    ,
    Xinyue Shen
    ,
    Ziyi Zhang
    ,
    Yule Liu
    ,
    Michael Backes
    ,
    Yang Zhang
    , Xinlei He
  4. Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models
    ACL 2025 ·
    Sibo Yi
    ,
    Tianshuo Cong
    , Xinlei He,
    Qi Li
    ,
    Jiaxing Song
  5. CHASM: Unveiling Covert Advertisements on Chinese Social Media
    NeurIPS 2025 ·
    Jingyi Zheng
    ,
    Tianyi Hu
    ,
    Yule Liu
    ,
    Zhen Sun
    ,
    Zongmin Zhang
    ,
    Zifan Peng
    ,
    Wenhan Dong
    , Xinlei He
  6. CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers
    AAAI 2025 ·
    Jingyi Zheng
    ,
    Tianyi Hu
    ,
    Tianshuo Cong
    , Xinlei He
  7. FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts
    EMNLP 2025 ·
    Ziyi Zhang
    ,
    Zhen Sun
    ,
    Zongmin Zhang
    ,
    Jihui Guo
    , Xinlei He
  8. FacLens: Transferable Probe for Foreseeing Non-Factuality in Fact-Seeking Question Answering of Large Language Models
    EMNLP 2025 ·
    Yanling Wang
    ,
    Haoyang Li
    ,
    Hao Zou
    ,
    Jing Zhang
    , Xinlei He,
    Qi Li
    ,
    Ke Xu
  9. From Purity to Peril: Backdooring Merged Models From "Harmless" Benign Components
    USENIX Security 2025 ·
    Lijin Wang
    ,
    Jingjing Wang
    ,
    Tianshuo Cong
    , Xinlei He,
    Zhan Qin
    ,
    Xinyi Huang
  10. On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writing
    SIGKDD 2025 ·
    Yule Liu
    ,
    Zhiyuan Zhong
    ,
    Yifan Liao
    ,
    Zhen Sun
    ,
    Jingyi Zheng
    ,
    Jiaheng Wei
    ,
    Qingyuan Gong
    ,
    Fenghua Tong
    ,
    Yang Chen
    ,
    Yang Zhang
    , Xinlei He
  11. PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning
    S&P 2025 ·
    Zhen Sun
    ,
    Tianshuo Cong
    ,
    Yule Liu
    ,
    Chenhao Lin
    , Xinlei He,
    Rongmao Chen
    ,
    Xingshuo Han
    ,
    Xinyi Huang
  12. Safety Misalignment Against Large Language Models
    NDSS 2025 ·
    Yichen Gong
    ,
    Delong Ran
    , Xinlei He,
    Tianshuo Cong
    ,
    Anyu Wang
    ,
    Xiaoyun Wang
  13. TH-Bench: Evaluating Evading Attacks via Humanizing AI Text on Machine-Generated Text Detectors
    SIGKDD 2025 ·
    Jingyi Zheng
    ,
    Junfeng Wang
    ,
    Zhen Sun
    ,
    Wenhan Dong
    ,
    Yule Liu
    , Xinlei He
  14. Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search
    USENIX Security 2025 ·
    Zeren Luo
    ,
    Zifan Peng
    ,
    Yule Liu
    ,
    Zhen Sun
    ,
    Mingchen Li
    ,
    Jingyi Zheng
    , Xinlei He
  15. MGTBench: Benchmarking Machine-Generated Text Detection
    CCS 2024 · Xinlei He,
    Xinyue Shen
    ,
    Zeyuan Chen
    ,
    Michael Backes
    ,
    Yang Zhang
  16. SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models
    USENIX Security 2024 ·
    Boyang Zhang
    ,
    Zheng Li
    ,
    Ziqing Yang
    , Xinlei He,
    Michael Backes
    ,
    Mario Fritz
    ,
    Yang Zhang
  17. Test-Time Poisoning Attacks Against Test-Time Adaptation Models
    S&P 2024 ·
    Tianshuo Cong
    , Xinlei He,
    Yun Shen
    ,
    Yang Zhang
  18. You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
    S&P 2024 · Xinlei He,
    Savvas Zannettou
    ,
    Yun Shen
    ,
    Yang Zhang