6 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…
ComMark: Covert and Robust Black-Box Model Watermarking with Compressed Samples
Yunfei Yang, Xiaojun Chen, Zhendong Zhao +3
The rapid advancement of deep learning has turned models into highly valuable assets due to their reliance on massive data and costly training processes. However, these models are…
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…
Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers
Xin Zhao, Xiaojun Chen, Bingshan Liu +3
Large language models (LLMs) with Mixture-of-Experts (MoE) architectures achieve impressive performance and efficiency by dynamically routing inputs to specialized subnetworks, kno…
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…
Antelope: Potent and Concealed Jailbreak Attack Strategy
Xin Zhao, Xiaojun Chen, Haoyu Gao
Due to the remarkable generative potential of diffusion-based models, numerous researches have investigated jailbreak attacks targeting these frameworks. A particularly concerning…