7 papers
Inferring Hidden User Models from the Behavior of Personalized LLM Agents
Haoyang Li, Yaxin Xiao, Qingqing Ye +2
Recent personalized LLM agents increasingly transform information retained in memory into compressed or structured representations, which we call user models, to guide later decisi…
MirageNet:A Secure, Efficient, and Scalable On-Device Model Protection in Heterogeneous TEE and GPU System
Huadi Zheng, Li Cheng, Yan Ding
As edge devices gain stronger computing power, deploying high-performance DNN models on untrusted hardware has become a practical approach to cut inference latency and protect user…
Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks
Yaxin Xiao, Qingqing Ye, Zi Liang +4
Machine learning models constitute valuable intellectual property, yet remain vulnerable to model extraction attacks (MEA), where adversaries replicate their functionality through…
Decision Potential Surface: A Theoretical and Practical Approximation of Large Language Model Decision Boundary
Zi Liang, Zhiyao Wu, Haoyang Shang +5
Decision boundary, the subspace of inputs where a machine learning model assigns equal classification probabilities to two classes, is pivotal in revealing core model properties an…
MER-Inspector: Assessing model extraction risks from an attack-agnostic perspective
Xinwei Zhang, Haibo Hu, Qingqing Ye +2
Information leakage issues in machine learning-based Web applications have attracted increasing attention. While the risk of data privacy leakage has been rigorously analyzed, the…
Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy
Yaxin Xiao, Qingqing Ye, Li Hu +5
Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to…