collaborators

32 papers

cs.CV2026

Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model

Sibo Wang, Jie Zhang, Shiguang Shan +2

While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks…

cs.CY2026

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…

cs.CV2026

Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating

Xiangkui Cao, Jie Zhang, Meina Kan +2

Large Vision-Language Models (LVLMs) have shown remarkable potential across a wide array of vision-language tasks, leading to their adoption in critical domains such as finance and…

cs.CV2026

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP

Sen Nie, Jie Zhang, Zhuo Wang +2

Vision-language models (VLMs) such as CLIP have demonstrated remarkable zero-shot generalization, yet remain highly vulnerable to adversarial examples (AEs). While test-time defens…

cs.RO2026

Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling

Xiaolong Tang, Meina Kan, Shiguang Shan +1

Safe and feasible trajectory planning is critical for real-world autonomous driving systems. However, existing learning-based planners rely heavily on expert demonstrations, which…

cs.CV2026

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…