Zi Liang

38 papers A* 9A 1B 1C 1Journal 24Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
AdDetector: Detecting Chinese Advertorials on Social Media Platforms with Textual and Social Information.
ACM Trans. Asian Low Resour. Lang. Inf. Process.
Haitao Bai, Pinghui Wang, Ruofei Zhang, Zi Liang, Ziyang Zhou, Zhou Su
2026 A* conf
Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks.
AAAI
Yaxin Xiao, Qingqing Ye, Zi Liang, Haoyang Li, Ronghua Li, Huadi Zheng, Haibo Hu
2026 A* conf
Decoding Web Memorization: A Semantic Membership Inference Attack on LLMs.
WWW
Zhiyao Wu, Zi Liang, Haibo Hu
2026 J jnl
FIT: Defying Catastrophic Forgetting in Continual LLM Unlearning.
CoRR
Xiaoyu Xu, Minxin Du, Kun Fang, Zi Liang, Yaxin Xiao, Zhicong Huang, Cheng Hong, Qingqing Ye, Haibo Hu
2026 J jnl
From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning.
CoRR
Xiaoyu Xu, Minxin Du, Zitong Li, Zi Liang, Zhibiao Guo, Shiyu Zhang, Peizhao Hu, Qingqing Ye, Haibo Hu
2026 A* conf
How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation Under the One-Time-Pad-Based Framework.
AAAI
Zi Liang, Liantong Yu, Shiyu Zhang, Qingqing Ye, Haibo Hu
2026 J jnl
How Much Information Can a Vision Token Hold? A Scaling Law for Recognition Limits in VLMs.
CoRR
Shuxin Zhuang, Zi Liang, Runsheng Yu, Hongzong Li, Rong Feng, Shiqin Tang, Youzhi Zhang
2026 J jnl
How Vulnerable Are Edge LLMs?
CoRR
Ao Ding, Hongzong Li, Zi Liang, Zhanpeng Shi, Shuxin Zhuang, Shiqin Tang, Rong Feng, Ping Lu
2025 — conf
"Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced Distillation.
ACL (1)
Zi Liang, Qingqing Ye, Yanyun Wang, Sen Zhang, Yaxin Xiao, Ronghua Li, Jianliang Xu, Haibo Hu
2025 J jnl
Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks.
CoRR
Yaxin Xiao, Qingqing Ye, Zi Liang, Haoyang Li, Ronghua Li, Huadi Zheng, Haibo Hu
2025 A* conf
Cross-Modal 3D Representation with Multi-View Images and Point Clouds.
CVPR
Ziyang Zhou, Pinghui Wang, Zi Liang, Haitao Bai, Ruofei Zhang
2025 J jnl
Decision Potential Surface: A Theoretical and Practical Approximation of LLM's Decision Boundary.
CoRR
Zi Liang, Zhiyao Wu, Haoyang Shang, Yulin Jin, Qingqing Ye, Huadi Zheng, Peizhao Hu, Haibo Hu
2025 A* conf
Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
ICML
Zi Liang, Haibo Hu, Qingqing Ye, Yaxin Xiao, Ronghua Li
2025 J jnl
Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
CoRR
Zi Liang, Haibo Hu, Qingqing Ye, Yaxin Xiao, Ronghua Li
2025 — conf
EEG-VL: Integrating Visual Features with Large Language Models for Automated Seizure Detection.
BIBM
Zi Liang, Peng Hu, Lian Li, Zebang Cheng, Yisu Dong, Haibo He, Qiang Lu, Nan Lin
2025 A* conf
Exploring Intrinsic Alignments Within Text Corpus.
AAAI
Zi Liang, Pinghui Wang, Ruofei Zhang, Haibo Hu, Shuo Zhang, Qingqing Ye, Nuo Xu, Yaxin Xiao, Chen Zhang, Lizhen Cui
2025 J jnl
How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework.
CoRR
Zi Liang, Liantong Yu, Shiyu Zhang, Qingqing Ye, Haibo Hu
2025 J jnl
How Vital Is the Jurisprudential Relevance: Law Article-Intervened Legal Case Retrieval and Matching.
ACM Trans. Inf. Syst.
Nuo Xu, Pinghui Wang, Zi Liang, Junzhou Zhao, Xiaohong Guan
2025 J jnl
How Vital is the Jurisprudential Relevance: Law Article Intervened Legal Case Retrieval and Matching.
CoRR
Nuo Xu, Pinghui Wang, Zi Liang, Junzhou Zhao, Xiaohong Guan
2025 J jnl
Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy.
CoRR
Yaxin Xiao, Qingqing Ye, Li Hu, Huadi Zheng, Haibo Hu, Zi Liang, Haoyang Li, Yijie Jiao
2025 J jnl
The Matthew Effect of AI Programming Assistants: A Hidden Bias in Software Evolution.
CoRR
Fei Gu, Zi Liang, Hongzong Li, Jiahao Ma
2025 J jnl
Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts.
CoRR
Li Bai, Qingqing Ye, Xinwei Zhang, Sen Zhang, Zi Liang, Jianliang Xu, Haibo Hu
2025 J jnl
United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory.
CoRR
Haoyang Shang, Xuan Liu, Zi Liang, Jie Zhang, Haibo Hu, Song Guo
2025 J jnl
Unlocking High-Fidelity Learning: Towards Neuron-Grained Model Extraction.
IEEE Trans. Dependable Secur. Comput.
Yaxin Xiao, Haibo Hu, Qingqing Ye, Li Tang, Zi Liang, Huadi Zheng
2025 J jnl
Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data.
CoRR
Zi Liang, Qingqing Ye, Xiang-Yang Alex Liu, Yanyun Wang, Jianliang Xu, Haibo Hu
2024 J jnl
Alignment-Aware Model Extraction Attacks on Large Language Models.
CoRR
Zi Liang, Qingqing Ye, Yanyun Wang, Sen Zhang, Yaxin Xiao, Ronghua Li, Jianliang Xu, Haibo Hu
2024 A* conf
MERGE: Fast Private Text Generation.
AAAI
Zi Liang, Pinghui Wang, Ruofei Zhang, Nuo Xu, Shuo Zhang, Lifeng Xing, Haitao Bai, Ziyang Zhou
2024 J jnl
New Paradigm of Adversarial Training: Breaking Inherent Trade-Off between Accuracy and Robustness via Dummy Classes.
CoRR
Yanyun Wang, Li Liu, Zi Liang, Qingqing Ye, Haibo Hu
2024 A* conf
PAIR: Pre-denosing Augmented Image Retrieval Model for Defending Adversarial Patches.
ACM Multimedia
Ziyang Zhou, Pinghui Wang, Zi Liang, Ruofei Zhang, Haitao Bai
2024 A conf
TSFool: Crafting Highly-Imperceptible Adversarial Time Series Through Multi-Objective Attack.
ECAI
Yanyun Wang, Dehui Du, Haibo Hu, Zi Liang, Yuanhao Liu
2024 J jnl
Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models.
CoRR
Zi Liang, Haibo Hu, Qingqing Ye, Yaxin Xiao, Haoyang Li
2024 J jnl
vEpiNet: A multimodal interictal epileptiform discharge detection method based on video and electroencephalogram data.
Neural Networks
Nan Lin, Weifang Gao, Lian Li, Junhui Chen, Zi Liang, Gonglin Yuan, Heyang Sun, Qing Li, Jianhua Chen, Liri Jin, Yan Huang, Xiangqin Zhou, Shaobo Zhang, Peng Hu, Chaoyue Dai, Haibo He, Yisu Dong, Liying Cui, Qiang Lu
2023 J jnl
Healing Unsafe Dialogue Responses with Weak Supervision Signals.
CoRR
Zi Liang, Pinghui Wang, Ruofei Zhang, Shuo Zhang, Xiaofan Ye, Yi Huang, Junlan Feng
2023 J jnl
MERGE: Fast Private Text Generation.
CoRR
Zi Liang, Pinghui Wang, Ruofei Zhang, Nuo Xu, Shuo Zhang
2023 A* conf
Multi-Action Dialog Policy Learning from Logged User Feedback.
AAAI
Shuo Zhang, Junzhou Zhao, Pinghui Wang, Tianxiang Wang, Zi Liang, Jing Tao, Yi Huang, Junlan Feng
2023 J jnl
Multi-Action Dialog Policy Learning from Logged User Feedback.
CoRR
Shuo Zhang, Junzhou Zhao, Pinghui Wang, Tianxiang Wang, Zi Liang, Jing Tao, Yi Huang, Junlan Feng
2018 C conf
Automatic Identification of Performance Bottleneck for A Complex Rendering System through Big Data.
CGI
Yanci Zhang, Zi Liang, Xiaoyao Li, Wenjie Ren, Yanli Liu
2016 B conf
SpongeNet: Towards bandwidth guarantees of cloud datacenter with two-phase VM placement.
NOMS
Hui Yu, Jiahai Yang, Cong Xu, Hui Wang, Zi Liang