PPaperPicks

Jinyuan Jia

29 papers at tracked venues · 26 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

USENIX Security ×6S&P ×5ACL ×3CVPR ×3AsiaCCS ×2ICLR ×2ICML ×2AAAI ×1CCS ×1ECCV ×1NDSS ×1NeurIPS ×1SIGKDD ×1

Frequent coauthors

Neil Zhenqiang Gong
×7
Yanting Wang
×6
Runpeng Geng
×5
Yupei Liu
×5
Wei Zou
×5
Binghui Wang
×5
Bo Li
×5
Yuqi Jia
×4
Dawn Song
×4
Zhangchen Xu
×4
Fengqing Jiang
×4
Luyao Niu
×4

Papers

  1. AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption
    S&P 2026 ·
    Yanting Wang
    ,
    Runpeng Geng
    ,
    Ying Chen
    , Jinyuan Jia
  2. PIArena: A Platform for Prompt Injection Evaluation
    ACL 2026 ·
    Runpeng Geng
    ,
    Chenlong Yin
    ,
    Yanting Wang
    ,
    Ying Chen
    , Jinyuan Jia
  3. PromptLocate: Localizing Prompt Injection Attacks
    S&P 2026 ·
    Yuqi Jia
    ,
    Yupei Liu
    ,
    Zedian Shao
    , Jinyuan Jia,
    Neil Zhenqiang Gong
  4. DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks
    S&P 2025 ·
    Yupei Liu
    ,
    Yuqi Jia
    , Jinyuan Jia,
    Dawn Song
    ,
    Neil Zhenqiang Gong
  5. Evaluating LLM-based Personal Information Extraction and Countermeasures
    USENIX Security 2025 ·
    Yupei Liu
    ,
    Yuqi Jia
    , Jinyuan Jia,
    Neil Zhenqiang Gong
  6. PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
    USENIX Security 2025 ·
    Wei Zou
    ,
    Runpeng Geng
    ,
    Binghui Wang
    , Jinyuan Jia
  7. Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
    ICLR 2025 ·
    Jiate Li
    ,
    Meng Pang
    ,
    Yun Dong
    , Jinyuan Jia,
    Binghui Wang
  8. Provably Robust Multi-bit Watermarking for AI-generated Text
    USENIX Security 2025 ·
    Wenjie Qu
    ,
    Wengrui Zheng
    ,
    Tianyang Tao
    ,
    Dong Yin
    ,
    Yanze Jiang
    ,
    Zhihua Tian
    ,
    Wei Zou
    , Jinyuan Jia,
    Jiaheng Zhang
  9. Stealing Training Graphs from Graph Neural Networks
    SIGKDD 2025 ·
    Minhua Lin
    ,
    Enyan Dai
    ,
    Junjie Xu
    , Jinyuan Jia,
    Xiang Zhang
    ,
    Suhang Wang
  10. TracLLM: A Generic Framework for Attributing Long Context LLMs
    USENIX Security 2025 ·
    Yanting Wang
    ,
    Wei Zou
    ,
    Runpeng Geng
    , Jinyuan Jia
  11. TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning
    AAAI 2025 ·
    Yupei Liu
    ,
    Yanting Wang
    , Jinyuan Jia
  12. ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learning
    USENIX Security 2024 ·
    Zhangchen Xu
    ,
    Fengqing Jiang
    ,
    Luyao Niu
    , Jinyuan Jia,
    Bo Li
    ,
    Radha Poovendran
  13. Certifiably Robust Image Watermark
    ECCV 2024 ·
    Zhengyuan Jiang
    ,
    Moyang Guo
    ,
    Yuepeng Hu
    , Jinyuan Jia,
    Neil Zhenqiang Gong
  14. Data Free Backdoor Attacks
    NeurIPS 2024 ·
    Bochuan Cao
    , Jinyuan Jia,
    Chuxuan Hu
    ,
    Wenbo Guo
    ,
    Zhen Xiang
    ,
    Jinghui Chen
    ,
    Bo Li
    ,
    Dawn Song
  15. Data Poisoning Based Backdoor Attacks to Contrastive Learning
    CVPR 2024 ·
    Jinghuai Zhang
    ,
    Hongbin Liu
    , Jinyuan Jia,
    Neil Zhenqiang Gong
  16. Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses
    CCS 2024 ·
    Yuxin Yang
    ,
    Qiang Li
    , Jinyuan Jia,
    Yuan Hong
    ,
    Binghui Wang
  17. FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models
    S&P 2024 ·
    Yanting Wang
    ,
    Wei Zou
    , Jinyuan Jia
  18. Formalizing and Benchmarking Prompt Injection Attacks and Defenses
    USENIX Security 2024 ·
    Yupei Liu
    ,
    Yuqi Jia
    ,
    Runpeng Geng
    , Jinyuan Jia,
    Neil Zhenqiang Gong
  19. GNNCert: Deterministic Certification of Graph Neural Networks against Adversarial Perturbations
    ICLR 2024 ·
    Zaishuo Xia
    ,
    Han Yang
    ,
    Binghui Wang
    , Jinyuan Jia
  20. Graph Neural Network Explanations are Fragile
    ICML 2024 ·
    Jiate Li
    ,
    Meng Pang
    ,
    Yun Dong
    , Jinyuan Jia,
    Binghui Wang
  21. Jailbreak Open-Sourced Large Language Models via Enforced Decoding
    ACL 2024 ·
    Hangfan Zhang
    ,
    Zhimeng Guo
    ,
    Huaisheng Zhu
    ,
    Bochuan Cao
    ,
    Lu Lin
    , Jinyuan Jia,
    Jinghui Chen
    ,
    Dinghao Wu
  22. MMCert: Provable Defense Against Adversarial Attacks to Multi-Modal Models
    CVPR 2024 ·
    Yanting Wang
    ,
    Hongye Fu
    ,
    Wei Zou
    , Jinyuan Jia
  23. POSTER: Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications
    AsiaCCS 2024 ·
    Fengqing Jiang
    ,
    Zhangchen Xu
    ,
    Luyao Niu
    ,
    Boxin Wang
    , Jinyuan Jia,
    Bo Li
    ,
    Radha Poovendran
  24. Poster: Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning
    AsiaCCS 2024 ·
    Zhangchen Xu
    ,
    Fengqing Jiang
    ,
    Luyao Niu
    , Jinyuan Jia,
    Radha Poovendran
  25. Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning
    S&P 2024 ·
    Hongbin Liu
    ,
    Wenjie Qu
    , Jinyuan Jia,
    Neil Zhenqiang Gong
  26. SHINE: Shielding Backdoors in Deep Reinforcement Learning
    ICML 2024 ·
    Zhuowen Yuan
    ,
    Wenbo Guo
    , Jinyuan Jia,
    Bo Li
    ,
    Dawn Song
  27. SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
    ACL 2024 ·
    Zhangchen Xu
    ,
    Fengqing Jiang
    ,
    Luyao Niu
    , Jinyuan Jia,
    Bill Yuchen Lin
    ,
    Radha Poovendran
  28. TextGuard: Provable Defense against Backdoor Attacks on Text Classification
    NDSS 2024 ·
    Hengzhi Pei
    , Jinyuan Jia,
    Wenbo Guo
    ,
    Bo Li
    ,
    Dawn Song
  29. Towards General Robustness Verification of MaxPool-Based Convolutional Neural Networks via Tightening Linear Approximation
    CVPR 2024 ·
    Yuan Xiao
    ,
    Shiqing Ma
    ,
    Juan Zhai
    ,
    Chunrong Fang
    , Jinyuan Jia,
    Zhenyu Chen