avatar

Jingyi Zheng

Ph.D. Student
HKUST(GZ)
ZJ10602@outlook.com


About Me

I am a second-year Ph.D. student at The Hong Kong University of Science and Technology (Guangzhou), advised by Prof. Xinlei He and Prof. Xinhu Zheng.

Research Interests

I work on trustworthy and secure AI systems, with recent interests extending to blockchain and embodied intelligence.

Trustworthy AI NLP Security & Privacy AI for Blockchain Embodied AI

News

Publications

  1. Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation
    ACL 2026 Main
    Tianyi Hu, Andrea Morales-Garzón, Jingyi Zheng, Maria Maistro, Daniel Hershcovich
    Annual Meeting of the Association for Computational Linguistics, Main Conference, Oral, 2026.
    Article
  2. JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models
    ICLR 2026
    Zifan Peng, Yule Liu, Zhen Sun, Mingchen Li, Zeren Luo, Jingyi Zheng, Wenhan Dong, Xinlei He, Xuechao Wang, Yingjie Xue, Shengmin Xu, Xinyi Huang
    International Conference on Learning Representations, 2026.
    Article
  3. 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
    Conference on Neural Information Processing Systems, Datasets and Benchmarks Track, 2025.
    Article Code Dataset
  4. The Rising Threat to Emerging AI-Powered Search Engines
    USENIX Security 2025
    Zeren Luo, Zifan Peng, Yule Liu, Zhen Sun, Mingchen Li, Jingyi Zheng, Xinlei He
    USENIX Security Symposium, 2025.
    Article
  5. On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writing
    KDD 2025
    Yule Liu, Zhiyuan Zhong, Yifan Liao, Zhen Sun, Jingyi Zheng, Jiaheng Wei, Qingyuan Gong, Fenghua Tong, Yang Chen, Yang Zhang, Xinlei He
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2025.
    Article Code
  6. TH-Bench: Evaluating Evading Attacks via Humanizing AI Text on Machine-Generated Text Detectors
    KDD 2025
    Jingyi Zheng*, Junfeng Wang*, Zhen Sun, Wenhan Dong, Yule Liu, Xinlei He
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2025.
    Article
  7. CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers
    AAAI 2025
    Jingyi Zheng*, Tianyi Hu*, Tianshuo Cong, Xinlei He
    Annual AAAI Conference on Artificial Intelligence, 2025.
    Article
  8. JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models
    NDSS 2025
    Delong Ran, Jinyuan Liu, Yichen Gong, Jingyi Zheng, Xinlei He, Tianshuo Cong, Anyu Wang
    Network and Distributed System Security Symposium, Best Technical Poster, 2025.
    Article Code
  9. A Two-Layer Blockchain Sharding Protocol Leveraging Safety and Liveness for Enhanced Performance
    NDSS 2024
    Yibin Xu, Jingyi Zheng, Boris Düdder, Tijs Slaats, Yongluan Zhou
    Network and Distributed System Security Symposium, 2024.
    Article
  10. Evaluation Hallucination in Multi-Round Incomplete Information Lateral-Driven Reasoning Tasks
    IJCAI Workshop 2025
    Wenhan Dong, Tianyi Hu, Jingyi Zheng, Zhen Sun, Yuemeng Zhao, Yule Liu, Xinlei He, Xinyi Huang
    IJCAI Workshop on User-Aligned Assessment of Adaptive AI Systems, 2025.
    Article
  11. AdSpectorX: A Multimodal Expert Spector for Covert Advertising Detection on Chinese Social Media
    SocialMeta 2024
    Zongmin Zhang, Yuhang Han, Zhen Sun, Yule Liu, Jingyi Zheng, Zhen Sun
    International Workshop on Social and Metaverse Computing, Sensing and Networking, Best Paper Award, 2024.
    Article
  12. Revealing the Difficulty in Jailbreak Defense on Language Models for Metaverse
    SocialMeta 2024
    Zuting Kang, Yule Liu, Jingyi Zheng, Zhen Sun
    International Workshop on Social and Metaverse Computing, Sensing and Networking, 2024.
    Article
  13. On the Generation and Mitigation of Harmful Geometry in Image-to-3D Models
    arXiv 2026
    Yule Liu, Yilong Yang, Jiale Teng, Hanze Jia, Zeren Luo, Jingyi Zheng, Zifan Peng, Ke Li, Yifan Liao, Zhen Sun, Jiaheng Wei, Yang Liu, Zhuo Ma, Xinlei He
    arXiv preprint, 2026.
    Article
  14. Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models
    arXiv 2025
    Yule Liu, Jingyi Zheng, Zhen Sun, Zifan Peng, Wenhan Dong, Zeyang Sha, Shiwen Cui, Weiqiang Wang, Xinlei He
    arXiv preprint, 2025.
    Article
  15. Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications
    arXiv 2025
    Wenhan Dong, Yuemeng Zhao, Zhen Sun, Yule Liu, Zifan Peng, Jingyi Zheng, Zongmin Zhang, Zhang Zhang, Jun Wu, Xinlei He, Xinyi Huang
    arXiv preprint, 2025.
    Article
  16. GasAgent: A Multi-Agent Framework for Automated Gas Optimization in Smart Contracts
    arXiv 2025
    Jingyi Zheng, Zifan Peng, Yule Liu, Junfeng Wang, Yifan Liao, Wenhan Dong, Xinlei He
    arXiv preprint, 2025.
    Article
  17. GRPO Privacy Is at Risk: A Membership Inference Attack Against Reinforcement Learning With Verifiable Rewards
    arXiv 2025
    Yule Liu, Heyi Zhang, Jingyi Zheng, Zhen Sun, Zifan Peng, Tianshuo Cong, Yibo Yang, Xinlei He, Zhuo Ma
    arXiv preprint, 2025.
    Article
  18. MATEX: A Multi-Agent Framework for Explaining Ethereum Transactions
    arXiv 2025
    Zifan Peng, Jingyi Zheng, Yule Liu, Hanze Jia, Qiming Ye, Jingyu Liu, Xufeng Yang, Mingchen Li, Qingyuan Gong, Xuechao Wang, Xinlei He
    arXiv preprint, 2025.
    Article
  19. ZPD-SCA: Unveiling the Blind Spots of LLMs in Assessing Students' Cognitive Abilities
    arXiv 2025
    Wenhan Dong, Zhen Sun, Yuemeng Zhao, Zifan Peng, Jun Wu, Jingyi Zheng, Yule Liu, Xinlei He, Yu Wang, Ruiming Wang, Xinyi Huang, Lei Mo
    arXiv preprint, 2025.
    Article