Publications
A collection of my research work.
* Equal contribution ✉ Corresponding author
[32]When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems
Jialuo Chen, Lingqi Jiang, Xinhao Deng, Xiaohu Du, Jianan Ma, Yunhao Feng, Yuqi Qing, Zhihao Yuan, Linkang Du, Jingyi Wang
arXiv 2026
[31]SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse
Jialuo Chen, Minghe Wang, Lingqi Jiang, Jianan Ma, Xinhao Deng, Xiaohu Du, Ruixiao Lin, Yunhao Feng, Linkang Du, Jingyi Wang
arXiv 2026
[30]Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents
Mingxiao Liu, Yitong Li, Haoren Zhao, Yaoxiang Bian, Jianan Ma, Jian Zhang, Jialuo Chen, Xinhao Deng✉, Zhen Wang✉
arXiv 2026
[28]Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Ruixiao Lin*, Xinhao Deng*, Qingming Li, Jianan Ma, Yunhao Feng, Yuqi Qing, Zhenyuan Li, Yechao Zhang, Shiwen Cui, Changhua Meng, Tianwei Zhang, Xingjun Ma, Qi Li, Ke Xu, Shouling Ji
arXiv 2026
[27]BraveGuard: From Open-World Threats to Safer Computer-Use Agents
Yunhao Feng, Xiaohu Du, Xinhao Deng, Yifan Ding, Ming Wen, Yixu Wang, Yuxiang Xie, Baihui Zheng, Yingshui Tan, Yige Li, Yutao Wu, Kerui Cao, Wenke Huang, Yanming Guo, Xingjun Ma, Yu-Gang Jiang
arXiv 2026
[26]AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents
Yixiang Zhang, Xinhao Deng, Jiaqing Wu, Yue Xiao, Ke Xu, Qi Li
arXiv 2026
[25]Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions
Jianan Ma, Xiaohu Du, Ruixiao Lin, Yaoxiang Bian, Jialuo Chen, Jingyi Wang, Xiaofang Yang, Shiwen Cui, Changhua Meng, Xinhao Deng✉, Zhen Wang✉
arXiv 2026
[24]Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats
Xinhao Deng, Yixiang Zhang, Jiaqing Wu, Jiaqi Bai, Sibo Yi, Zhuoheng Zou, Yue Xiao, Rennai Qiu, Jianan Ma, Jialuo Chen, Xiaohu Du, Xiaofang Yang, Shiwen Cui, Changhua Meng, Weiqiang Wang, Jiaxing Song, Ke Xu, Qi Li
arXiv 2026
[23]Automating Agent Hijacking via Structural Template Injection
Xinhao Deng*, Jiaqing Wu*, Miao Chen, Yue Xiao, Ke Xu, Qi Li
arXiv 2026
[22]Towards Robust Multi-tab Website Fingerprinting
Xinhao Deng, Xiyuan Zhao, Qilei Yin, Zhuotao Liu, Qi Li, Mingwei Xu, Ke Xu, Jianping Wu
IEEE/ACM Transactions on Networking (ToN) 2026
[21]Towards Robust Detection of Malicious Encrypted Traffic Using Only Low-Quality Training Data
Yuqi Qing, Qilei Yin, Xinhao Deng, Yihao Chen, Zhuotao Liu, Kun Sun, Ke Xu, Jia Zhang, Qi Li
IEEE/ACM Transactions on Networking (ToN) 2026
[20]Robust LLM-Based Website Fingerprinting under Dynamic Real-World Conditions
Xiyuan Zhao, Xinhao Deng, Tianyu Cui, Yixiang Zhang, Ke Xu, Qi Li
ACM Web Conference (WWW) 2026
[19]STAR: Semantic-Traffic Alignment and Retrieval for Zero-Shot HTTPS Website Fingerprinting
Yifei Cheng, Yujia Zhu, Baiyang Li, Xinhao Deng, Yitong Cai, Yaochen Ren, Qingyun Liu
IEEE INFOCOM 2026
[18]From Length to Content: Token-Length Side-Channel Attacks on Merged LLM API Outputs
Sijia Li, Tianyu Cui, Miao Chen, Xinjie Lin, Zheyuan Gu, Xinhao Deng, Ke Xu, Qi Li
USENIX Security Symposium 2026
[17]Towards Practical Few-shot Multi-tab Website Fingerprinting
Lin Liu, Ziling Wei, Zhuotao Liu, Xinhao Deng, Zixuan Dong, Shuhui Chen
USENIX Security Symposium 2026
[16]Enhancing Website Fingerprinting Attacks against Traffic Drift
Xinhao Deng, Yixiang Zhang, Qi Li, Zhuotao Liu, Yabo Wang, Ke Xu
Network and Distributed System Security Symposium (NDSS) 2026
[15]Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions
Yixiang Zhang, Xinhao Deng, Zhongyi Gu, Yihao Chen, Ke Xu, Qi Li, Jianping Wu
arXiv 2025
[14]Beyond a Single Perspective: Towards a Realistic Evaluation of Website Fingerprinting Attacks
Xinhao Deng, Jingyou Chen, Linxiao Yu, Yixiang Zhang, Zhongyi Gu, Changhao Qiu, Xiyuan Zhao, Ke Xu, Qi Li
Tsinghua Science and Technology (TST) 2025
[13]Training Robust Classifiers for Classifying Encrypted Traffic under Dynamic Network Conditions
Yuqi Qing, Qilei Yin, Xinhao Deng, Xiaoli Zhang, Peiyang Li, Zhuotao Liu, Kun Sun, Ke Xu, Qi Li
ACM Conference on Computer and Communications Security (CCS) 2025
[12]HOLMES & WATSON: A Robust and Lightweight HTTPS Website Fingerprinting through HTTP Version Parallelism
Yifei Cheng, Yujia Zhu, Baiyang Li, Peishuai Sun, Yong Ding, Xinhao Deng, Qingyun Liu
ACM Web Conference (WWW) 2025
[11]Wedjat: Detecting Sophisticated Evasion Attacks via Real-time Causal Analysis
Li Gao, Chuanpu Fu, Xinhao Deng, Ke Xu, Qi Li
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2025
[10]Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems
Tianyu Cui, Yanling Wang, Chuanpu Fu, Yong Xiao, Sijia Li, Xinhao Deng, Yunpeng Liu, Qinglin Zhang, Ziyi Qiu, Peiyang Li, Zhixing Tan, Junwu Xiong, Xinyu Kong, Zujie Wen, Ke Xu, Qi Li
arXiv 2024
[7]Exploring Dynamic Rule Caching Under Dependency Constraints for Programmable Switches: Theory, Algorithm, and Implementation
Xinhao Deng, Mingwei Xu, Qi Li, Weijie Wu, Yuan Yang, Menghao Zhang, Yu Zhou, Jianping Wu
IEEE Transactions on Network and Service Management (TNSM) 2024
[4]Unsupervised and Adaptive Tor Website Fingerprinting
Guoqiang Zhang, Jiahao Cao, Mingwei Xu, Xinhao Deng
EAI International Conference on Security and Privacy in Communication Networks (SecureComm) 2023
[3]Dynamic Network Function Enforcement via Joint Flow and Function Scheduling
Qi Li, Xinhao Deng, Zhuotao Liu, Yuan Yang, Xiaoyue Zou, Mingwei Xu, Jianping Wu
IEEE Transactions on Information Forensics and Security (TIFS) 2022
[2]Practical Differentially Private Online Advertising
Jie Sun, Lingchen Zhao, Zhuotao Liu, Qi Li, Xinhao Deng, Qian Wang, Yong Jiang
Computers & Security 2022
[1]FISE: A Forwarding Table Structure for Enterprise Networks
Shu Yang, Laizhong Cui, Xinhao Deng, Qi Li, Yulei Wu, Mingwei Xu, Jianping Wu
IEEE Transactions on Network and Service Management (TNSM) 2019