4 papers · 1 filter
Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures
Zeyao Liu, Zhendong Zhao, Xiaojun Chen +3
Existing ViT backdoor attacks based on backbone-overwriting full-tuning are computationally expensive and inflict performance degradation. This has forced adversaries towards the V…
DeepTracer: Tracing Stolen Model via Deep Coupled Watermarks
Yunfei Yang, Xiaojun Chen, Yuexin Xuan +3
Model watermarking techniques can embed watermark information into the protected model for ownership declaration by constructing specific input-output pairs. However, existing wate…
Model-Guardian: Protecting against Data-Free Model Stealing Using Gradient Representations and Deceptive Predictions
Yunfei Yang, Xiaojun Chen, Yuexin Xuan +1
Model stealing attack is increasingly threatening the confidentiality of machine learning models deployed in the cloud. Recent studies reveal that adversaries can exploit data synt…
Practical and General Backdoor Attacks against Vertical Federated Learning
Yuexin Xuan, Xiaojun Chen, Zhendong Zhao +2
Federated learning (FL), which aims to facilitate data collaboration across multiple organizations without exposing data privacy, encounters potential security risks. One serious t…