Jiaming Zhang

Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal Reasoning Models

Severing the Link: A Unified Adversarial Attack on Image and Video MLLMs via Generative Disruption

TrojanTools: Adaptive Indirect Prompt Injection on LLM Agents via Malicious Tool-Calling

AnyAttack: Self-supervised Generation of Targeted Adversarial Attacks for Vision-Language Models

Debiasing Vison-Language Models with Text-Only Training