7 papers
DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs
Anqi Li, Jie Zhang, Zhongqi Wang +4
While Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases. Existing bias evaluation protocols predomi…
EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy
Xuanyu Ge, Zhongqi Wang, Jie Zhang +2
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to backdoor attacks. Existing defense methods predom…
What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Models
Sen Nie, Jie Zhang, Zhongqi Wang +3
Achieving adversarial robustness in Vision-Language Models (VLMs) inevitably compromises accuracy on clean data, presenting a long-standing and challenging trade-off. In this work,…
Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models
Zhongqi Wang, Jie Zhang, Shiguang Shan +1
Recent studies have revealed that text-to-image diffusion models are vulnerable to backdoor attacks, where attackers implant stealthy textual triggers to manipulate model outputs.…
Assimilation Matters: Model-level Backdoor Detection in Vision-Language Pretrained Models
Zhongqi Wang, Jie Zhang, Shiguang Shan +1
Vision-language pretrained models (VLPs) such as CLIP have achieved remarkable success, but are also highly vulnerable to backdoor attacks. Given a model fine-tuned by an untrusted…
Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion Models
Jie Zhang, Zhongqi Wang, Shiguang Shan +1
Backdoor attacks targeting text-to-image diffusion models have advanced rapidly. However, current backdoor samples often exhibit two key abnormalities compared to benign samples: 1…