24 papers
InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language Models
Chengyin Hu, Dingyi Lu, Jiaju Han +5
Infrared vision-language models (IR-VLMs) have emerged as a promising paradigm for multimodal perception under low-visibility conditions, yet their robustness to targeted adversari…
AdvTiles: Physical Adversarial Camouflage Clothing against Person Detectors via Learnable Tiles
Jinlei Wang, Jiahuan Long, Mingkai Sun +9
Physical adversarial attacks against person detectors have evolved from localized patches to full-body textures. However, achieving both visual naturalness and strong attack effect…
Radar4D-VLM: Proposal-Grounded Temporal 4D Radar Reasoning Across Frozen Language Models
Jiaju Han, Xuemeng Sun, Qike Zhang +6
Vision-language models for autonomous driving primarily rely on cameras and LiDAR, leaving 4D radar largely unexplored as a standalone perceptual modality despite its robustness to…
QR-Structured Thermal Triggers for Targeted Semantic Attacks on Infrared Vision-Language Models
Xiang Chen, Yingying Zhao, Chao Li +7
Infrared vision-language models (IR-VLMs) extend thermal perception to open-vocabulary classification, image captioning, and visual question answering. However, their robustness to…
InfraQR: Edge-Placed QR-Inspired Structured Patch Attacks on Infrared Vision-Language Models
Xin Li, Jiaju Han, Ma Yaqi +5
Infrared vision-language models are increasingly used for perception under low-light and adverse visual conditions, yet their robustness to localized structured perturbations remai…
MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation
Jiaju Han, Ma Yaqi, Yahui Chai +8
Infrared remote-sensing imagery captures intensity structure, object-background contrast, and illumination-invariant cues often invisible in RGB imagery. Yet, most remote-sensing v…
AirflowAttack: Thermal-Airflow Adversarial Perturbations against Infrared Remote-Sensing Vision-Language Models
Cong Su, Jiaju Han, Xuemeng Sun +5
Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their adversarial robustness remains unexamined.…
Exposing Vulnerabilities in Visible-Infrared VLMs: A Unified Geometric Adversarial Framework with Cross-Task Transferability
Xiang Chen, Yuxian Dong, Chao Li +6
Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, but their adversarial robustness in visible-infrared (VIS-IR) scenarios remains unde…
From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG
Jiaju Han, Chao Li, Chengyin Hu +8
Multimodal RAG systems increasingly rely on vision-language retrievers to ground visual queries in external textual evidence. Existing adversarial studies on RAG mainly manipulate…
When Surfaces Lie: Exploiting Wrinkle-Induced Attention Shift to Attack Vision-Language Models
Chengyin Hu, Xuemeng Sun, Jiaju Han +5
Visual-Language Models (VLMs) have demonstrated exceptional cross-modal understanding across various tasks, including zero-shot classification, image captioning, and visual questio…
Challenging Vision-Language Models with Physically Deployable Multimodal Semantic Lighting Attacks
Yingying Zhao, Chengyin Hu, Qike Zhang +7
Vision-Language Models (VLMs) have shown remarkable performance, yet their security remains insufficiently understood. Existing adversarial studies focus almost exclusively on the…
CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models
Xiang Chen, Fangfang Yang, Chunlei Meng +6
Medical vision--language models (MVLMs) are increasingly used as perceptual backbones in radiology pipelines and as the visual front end of multimodal assistants, yet their reliabi…
JailWAM: Jailbreaking World Action Models in Robot Control
Hanqing Liu, Songping Wang, Jiahuan Long +9
World Action Models (WAMs) have emerged as a promising paradigm for robotic manipulation, enabling physical interaction across diverse tasks and environments. However, their abilit…
Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patch for Infrared Vision-Language Models
Chengyin Hu, Yuxian Dong, Yikun Guo +8
Infrared vision-language models (IR-VLMs) are becoming important for semantic perception in low-visibility environments, yet their robustness to physical semantic attacks remains u…
XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMs
Chengyin Hu, Jiaju Han, Xuemeng Sun +6
Vision-language models (VLMs) share visual-textual representations across zero-shot classification, image captioning, and visual question answering (VQA), creating a pathway throug…
Thermal Topology Collapse: Universal Physical Patch Attacks on Infrared Vision Systems
Chengyin Hu, Yikun Guo, Yuxian Dong +7
Infrared pedestrian detectors are increasingly deployed in all-weather perception systems, but their robustness against physical adversarial attacks remains insufficiently understo…
Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems
Jiahuan Long, Tingsong Jiang, Hanqing Liu +4
Adversarial patches have emerged as a popular privacy-preserving approach for resisting AI-driven surveillance systems. However, their conspicuous appearance makes them difficult t…
Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variations
Hanqing Liu, Shouwei Ruan, Jiahuan Long +6
Vision-Language-Action (VLA) models have emerged as promising solutions for robotic manipulation, yet their robustness to real-world physical variations remains critically underexp…
FR-Mamba: Time-Series Physical Field Reconstruction Based on State Space Model
Jiahuan Long, Wenzhe Zhang, Ning Wang +2
Physical field reconstruction (PFR) aims to predict the state distribution of physical quantities (e.g., velocity, pressure, and temperature) based on limited sensor measurements.…
LMDepth: Lightweight Mamba-based Monocular Depth Estimation for Real-World Deployment
Jiahuan Long, Xin Zhou
Monocular depth estimation provides an additional depth dimension to RGB images, making it widely applicable in various fields such as virtual reality, autonomous driving and robot…
PapMOT: Exploring Adversarial Patch Attack against Multiple Object Tracking
Jiahuan Long, Tingsong Jiang, Wen Yao +5
Tracking multiple objects in a continuous video stream is crucial for many computer vision tasks. It involves detecting and associating objects with their respective identities acr…
Robust SAM: On the Adversarial Robustness of Vision Foundation Models
Jiahuan Long, Zhengqin Xu, Tingsong Jiang +4
The Segment Anything Model (SAM) is a widely used vision foundation model with diverse applications, including image segmentation, detection, and tracking. Given SAM's wide applica…
CDUPatch: Color-Driven Universal Adversarial Patch Attack for Dual-Modal Visible-Infrared Detectors
Jiahuan Long, Wen Yao, Tingsong Jiang +1
Adversarial patches are widely used to evaluate the robustness of object detection systems in real-world scenarios. These patches were initially designed to deceive single-modal de…
Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models
Jiahuan Long, Tingsong Jiang, Wen Yao +5
Vision foundation models (VFMs) have demonstrated remarkable capabilities in learning universal visual representations. However, adapting these models to downstream tasks conventio…