📝 Selected Papers

(*: Equal Contribution, ^: Corresponding Author)

• WebCloak: Characterizing and Mitigating the Threats of LLM-Driven Web Agents as Intelligent Scrapers IEEE S&P 2026 [Website]
  Xinfeng Li, Tianze Qiu, Yingbin Jin, Lixu Wang, Hanqing Guo, Xiaojun Jia, XiaoFeng Wang, Wei Dong.

• EmoRAG: Evaluating RAG Robustness to Symbolic Perturbations SIGKDD 2026
  Xinyun Zhou*, Xinfeng Li*, Yinan Peng, Ming Xu, Xuanwang Zhang, Miao Yu, Yidong Wang, Xiaojun Jia, Kun Wang, Qingsong Wen, XiaoFeng Wang, Wei Dong.

• EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models IEEE S&P 2026
  Jialin Wu, Kecen Li, Zhicong Huang, Xinfeng Li, XiaoFeng Wang, Cheng Hong.

• Critical Information Only: A Content Privacy-Preserving Framework for Detecting Audio Deepfakes TDSC 2026
  Xinfeng Li, Yifan Zheng, Chen Yan, Kai Li, Chang Zeng, Xiaoyu Ji, Wenyuan Xu.

• RACONTEUR: A Knowledgeable, Insightful, and Portable LLM-Powered Shell Command Explainer NDSS 2025 [Website]
  Jiangyi Deng*, Xinfeng Li*, Yanjiao Chen, Yijie Bai, Haiqin Weng, Yan Liu, Tao Wei, Wenyuan Xu.

• Neural Invisibility Cloak: Concealing Adversary in Images via Compromised AI-driven Image Signal Processing USENIX Security 2025
  Wenjun Zhu, Xiaoyu Ji, Xinfeng Li, Qihang Chen, Kun Wang, Xinyu Li, Ruoyan Xu, Wenyuan Xu.

• LightAntenna: Characterizing the Limits of Fluorescent Lamp-Induced Electromagnetic Interference NDSS 2025
  Fengchen Yang, Wenze Cui, Xinfeng Li, Chen Yan, Xiaoyu Ji, Wenyuan Xu.

• AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents NeurIPS 2025
  Hanjun Luo, Shenyu Dai, Chiming Ni, Xinfeng Li^, Guibin Zhang, Kun Wang, Tongliang Liu, Hanan Salam.

• AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models Responsible Foundation Models at NeurIPS 2025
  K. Li, C. Shen, Y. Liu, J. Han, K. Zheng, X. Zou, Z. Wang, S. Zhang, X. Du, H. Luo, Y. Jin, X. Xing, Z. Ma, Y. Liu, Y. Zhang, J. Fang, K. Wang, Y. Yan, G. Deng, H. Li, Y. Li, X. Zhuang, T. Chen, Q. Wen, T. Zhang, Y. Liu, H. Hu, Z. Wu, X. Hu, E. Chng, W. Xu, X. Wang, W. Dong, Xinfeng Li^.

• A Survey on Trustworthy LLM Agents: Threats and Countermeasures SIGKDD 2025
  Miao Yu, Fanci Meng, Xinyun Zhou, Shilong Wang, Junyuan Mao, Linsey Pang, Tianlong Chen, Kun Wang, Xinfeng Li^, Yongfeng Zhang, Bo An, Qingsong Wen.

• Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries
  Xinfeng Li*, Shengyuan Pang*, Jialin Wu, Jiangyi Deng, Huanlong Zhong, Yanjiao Chen, Jie Zhang, Wenyuan Xu

• A Vision for Access Control in LLM-based Agent Systems
  Xinfeng Li, Dong Huang, Jie Li, Hongyi Cai, Zhenhong Zhou, Wei Dong, XiaoFeng Wang, Yang Liu.

• The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework MM 2025
  Feiran Liu, Yuzhe Zhang, Xinyi Huang, Yinan Peng, Xinfeng Li^, Lixu Wang, Yutong Shen, Ranjie Duan, Simeng Qin, Xiaojun Jia, Qingsong Wen, Wei Dong.

• SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models ACM CCS 2024 [Code][Weights]
  Xinfeng Li, Yuchen Yang, Jiangyi Deng, Chen Yan, Yanjiao Chen, Xiaoyu Ji, Wenyuan Xu.

• SafeEar: Content Privacy-Preserving Audio Deepfake Detection ACM CCS 2024 [Website][Dataset][Code]
  Xinfeng Li, Kai Li, Yifan Zheng, Chen Yan, Xiaoyu Ji, Wenyuan Xu.

• Legilimens: Practical and Unified Content Moderation for Large Language Model Services ACM CCS 2024 [Code]
  Jialin Wu, Jiangyi Deng, Shengyuan Pang, Yanjiao Chen, Jiayang Xu, Xinfeng Li, Wenyuan Xu.

• Inaudible Adversarial Perturbation: Manipulating the Recognition of User Speech in Real Time NDSS 2024 [Website1][Website2][Code]
  Xinfeng Li, Chen Yan, Xuancun Lu, Zihan Zeng, Xiaoyu Ji, Wenyuan Xu.

• Learning Normality is Enough: A Software-Based Mitigation Against Inaudible Voice Attacks USENIX Security 2023 [Website]
  Xinfeng Li, Xiaoyu Ji, Chen Yan, Chaohao Li, Yichen Li, Zhenning Zhang, Wenyuan Xu.

• Scoring Metrics of Assessing Voiceprint Distinctiveness based on Speech Content and Rate IEEE TDSC 2024
  Ruiwen He, Yushi Cheng, Junning Ze, Xinfeng Li, Xiaoyu Ji, Wenyuan Xu.

• Detecting Inaudible Voice Commands via Acoustic Attenuation by Multi-channel Microphones IEEE TDSC 2024
  Xiaoyu Ji, Guoming Zhang, Xinfeng Li, Gang Qu, Xiuzhen Cheng, Wenyuan Xu.

• Enrollment-Stage Backdoor Attacks on Speaker Recognition Systems via Adversarial Ultrasound IEEE IoT-J 2023
  Xinfeng Li, Junning Ze, Chen Yan, Yushi Cheng, Xiaoyu Ji, Wenyuan Xu.

• Toward Pitch-Insensitive Speaker Verification via Soundfield IEEE IoT-J 2023
  Xinfeng Li, Zhicong Zheng, Chen Yan, Chaohao Li, Xiaoyu Ji, Wenyuan Xu.

• The Silent Manipulator: A Practical and Inaudible Backdoor Attack against Speech Recognition Systems ACM MM 2023
  Zhicong Zheng, Xinfeng Li, Chen Yan, Xiaoyu Ji, Wenyuan Xu.

• “OK, Siri” or “Hey, Google”: Evaluating Voiceprint Distinctiveness Via Content-based PROLE Score USENIX Security 2022 [Website]
  Ruiwen He, Xiaoyu Ji, Xinfeng Li, Yushi Cheng, Wenyuan Xu.

• EarArray: Defending against DolphinAttack via Acoustic Attenuation NDSS 2021
  Guoming Zhang, Xiaoyu Ji, Xinfeng Li, Gang Qu, Wenyuan Xu.