10 papers
Neos: Learning to Interleave Search and Visual Reasoning
Ekko He, Jack Hong, Shilin Yan +8
Recent multimodal deep search agents have advanced tool use and visual content retrieval, yet they still struggle to convert intermediate visual evidence into actionable guidance f…
Beyond Token Importance: Preserving Spatial Scaffolds for Efficient Vision-Language-Action Inference
Jiayu Chen, Shuyong Gao, Jingkai Jia +6
Existing VLA pruning strategies primarily select individual visual tokens according to task-level semantic relevance, while overlooking the spatial information required for robotic…
VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking
Jiyuan Fu, Kaixun Jiang, Jingkai Jia +7
While Vision-Language-Action (VLA) models have emerged as powerful generalist policies, their severe vulnerability to adversarial patches significantly hinders their deployment in…
RSAgent: Learning to Reason and Act for Text-Guided Segmentation via Multi-Turn Tool Invocations
Xingqi He, Yujie Zhang, Shuyong Gao +6
Text-guided object segmentation requires both cross-modal reasoning and pixel grounding abilities. Most recent methods treat text-guided segmentation as one-shot grounding, where t…
Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
Kaixun Jiang, Zhaoyu Chen, Haijing Guo +6
Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted ad…
LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops
Jiyuan Fu, Kaixun Jiang, Lingyi Hong +5
Multimodal Large Language Models (MLLMs) have shown great promise but require substantial computational resources during inference. Attackers can exploit this by inducing excessive…
VideoPure: Diffusion-based Adversarial Purification for Video Recognition
Kaixun Jiang, Zhaoyu Chen, Jiyuan Fu +3
Recent work indicates that video recognition models are vulnerable to adversarial examples, posing a serious security risk to downstream applications. However, current research has…
Boosting Adversarial Transferability with Spatial Adversarial Alignment
Zhaoyu Chen, Haijing Guo, Kaixun Jiang +6
Deep neural networks are vulnerable to adversarial examples that exhibit transferability across various models. Numerous approaches are proposed to enhance the transferability of a…
PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving
Jiyuan Fu, Zhaoyu Chen, Kaixun Jiang +3
Vision foundation models are increasingly employed in autonomous driving systems due to their advanced capabilities. However, these models are susceptible to adversarial attacks, p…
Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction
Jiyuan Fu, Zhaoyu Chen, Kaixun Jiang +4
Despite the substantial advancements in Vision-Language Pre-training (VLP) models, their susceptibility to adversarial attacks poses a significant challenge. Existing work rarely s…