My Publications
My Publications
Accepted Papers:
2025
Peizhuo Lv, Mengjie Sun, Hao Wang, Xiaofeng Wang, Shengzhi Zhang, Yuxuan Chen, Kai Chen, Limin Sun. "RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models", The ACM Conference on Computer and Communications Security (CCS) 2025. (CCF A) [pdf of Extended Version]
Zhicheng Zhang*, Peizhuo Lv* (co-first Author), Mengke Wan, Jiang Fang, Diandian Guo, Yezeng Chen, Yinlong Liu, Wei Ma, Jiyan Sun, Liru Geng. "Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution", ACM MM 2025. (CCF-A) [pdf]
Yu Peng, Lijie Zhang, Peizhuo Lv (Corresponding Author), Kai Chen. "RepeatLeakage: leak prompts from repeating as Large language model is a good repeater", Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI) 2025. (CCF A) [pdf]
Shuguang Yuan, Xingyu Su, Peizhuo Lv, Weijie xue, Jing Yu, Xiaojie Zhu, Chi Chen. "An Efficient White-box LLM Watermarking for IP Protection on Online Market Platforms", 31st SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2025. (CCF A) [pdf]
Pan Li, Peizhuo Lv (Corresponding Author), Kai Chen, Shengzhi Zhang, Yuling Cai, Fan Xiang. "A Model Stealing Attack Against Multi-exit Networks", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2025 (CCF B) [pdf]
2024
Peizhuo Lv, Hualong Ma, Kai Chen, Jiachen Zhou, Shengzhi Zhang, Ruigang Liang, et al. "MEA-Defender: A Robust Watermark against Model Extraction Attack", IEEE Symposium on Security and Privacy (S&P) 2024. (CCF A) [pdf]
Peizhuo Lv, Pan Li, Shenchen Zhu, Shengzhi Zhang, Kai Chen, Ruigang Liang, et al. "SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-Supervised Learning", The Network and Distributed System Security Symposium (NDSS) 2024. (CCF A) [pdf]
Hualong Ma*, Peizhuo Lv* (co-first Author), Kai Chen, Jiachen Zhou. "KGDist: A Prompt-Based Distillation Attack against LMs Augmented with Knowledge Graphs". The 27th International Symposium on Research in Attacks, Intrusions and Defenses (RAID) 2024. (CCF B) [pdf]
Jiachen Zhou, Peizhuo Lv, Yibing Lan, Guozhu Meng, Kai Chen, Hualong Ma, "DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models". In Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), 2024. (CCF A) [pdf]
2023
Peizhuo Lv, Chang Yue, Ruigang Liang, Yunfei Yang, Shengzhi Zhang, Hualong Ma, Kai Chen, "A Data-free Backdoor Injection Approach in Neural Networks". In Proceedings of the 32nd USENIX Security, 2023. (CCF A) [pdf] [video]
Peizhuo Lv, Pan Li, Shengzhi Zhang, Kai Chen, Ruigang Liang, Hualong Ma, Yue Zhao, Yingjiu Li, "A Robustness-Assured White-Box Watermark in Neural Networks". In IEEE Transactions on Dependable and Secure Computing (IEEE TDSC), 2023. (CCF A) [pdf]
Peizhuo Lv, Hualong Ma, Jiachen Zhou, Ruigang Liang, Kai Chen, Shengzhi Zhang, Yunfei Yang, "DBIA: Data-free backdoor injection attack against transformer networks", In IEEE International Conference on Multimedia & Expo (ICME), 2023. (CCF B) [pdf]
Chengan Wei, Yeonjoon Lee, Kai Chen, Guozhu Meng, Peizhuo Lv, "Aliasing Backdoor Attacks on Pre-trained Models". In Proceedings of the 32nd USENIX Security, 2023. (CCF A) [pdf]
Chang Yue, Peizhuo Lv, Ruigang Liang, Kai Chen, "Invisible Backdoor Attacks Using Data Poisoning in Frequency Domain". In 26th European Conference on Artificial Intelligence (ECAI), 2023. (CCF B) [pdf]
2020-2022