InfraPatch is a white‑box, per‑instance framework that generates small grayscale patches to target infrared‑adapted vision‑language models (IR‑VLMs). The method optimizes a single‑channel patch within a 5% local‑area budget, using proxy‑guided placement and task‑adaptive objectives to induce desired behaviors in image classification, captioning, and binary visual question answering. Across ten IR‑VLM variants tested on synthetic infrared images, InfraPatch achieves targeted attack success rates ranging from 86% to 100%, revealing significant vulnerability differences among architectures and tasks.
By Chengyin Hu, Dingyi Lu, Jiaju Han, Xiang Chen, Weiwen Shi, Jiahuan Long, Yiwei Wei, Jiujiang Guo
arXiv:2610.32230v1 Announce Type: new
Abstract: Modern autonomous driving systems widely adopt multi-view Bird's-Eye-View (BEV) based 3D perception models due to their superior performance. Despite t...
By Linye Lyu, Jiawei Zhou, Daojing He, Yu Li
The paper introduces a unified evaluation framework for assessing the physical adversarial robustness of Vision‑Language Models (VLMs) deployed at the edge. It defines a conditional attack success rate (cASR) metric that counts only images where the model still localizes objects under a gray occluder, and categorizes failures into omission, substitution, and displacement. Benchmarking shows that compact grounding VLMs can be as vulnerable as traditional object detectors, with omission being the only failure visible to downstream systems, while displacement and substitution pose potentially more dangerous risks, especially under distribution shift.
By Eric Liang, Alan Luo, Kaiwen Yuan
arXiv:2607. 06485v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their adversarial robustness remains unexamined.
By Cong Su, Jiaju Han, Xuemeng Sun, Chengyin Hu, Qike Zhang, Jiujiang Guo, Yiwei Wei, Jiahuan Long
Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their adversarial robustness remains unexamined. We present AirflowAttack, to our knowledge the first adversarial attack for IR remote-sensing VLMs and the first to weaponize thermal-airflow turbulence as the perturbation prior.
arXiv:2606. 17711v1 Announce Type: cross Abstract: Pixel-wise adversarial patches are computationally heavy and often visually detectable, limiting utility in security-critical systems.
By Jens Bayer, Stefan Becker, David M\"unch, Michael Arens, J\"urgen Beyerer
arXiv:2509.06422v2 Announce Type: replace
Abstract: Video camouflaged object detection (VCOD) is challenging due to dynamic environments. Existing methods face two main issues: (1) SAM-based methods...
By Hua Zhang, Changjiang Luo
The paper investigates using diffusion-based generative image editing to improve object detector robustness against domain shifts, specifically camouflaged military vehicle detection. By synthetically adding foliage, netting, and multi‑spectral camouflage to training data with models such as Qwen Image Edit 2509 and Flux.2 Dev, the authors demonstrate significant mAP gains (up to +20.1 for foliage) over detectors trained on uncamouflaged data. LoRA fine‑tuning further boosts performance for the more challenging multi‑spectral camouflage.
By Isabel D. Stein, Thijs A. Eker, Sebastiaan P. Snel, Ella P. Fokkinga, Klamer Schutte, Luca Ambrogioni, Friso G. Heslinga
ComplicitSplat is a novel black‑box attack that leverages 3D Gaussian Splatting (3DGS) shading to create viewpoint‑specific camouflage, embedding adversarial content into scene objects that is only visible from certain angles. The method does not require access to model architecture or weights and can successfully fool a range of popular object detectors—including single‑stage, multi‑stage, and transformer‑based models—on both real‑world physical objects and synthetic scenes. This demonstrates that downstream models using 3DGS are vulnerable to adversarial manipulation.
By Matthew Hull, Haoyang Yang, Pratham Mehta, Mansi Phute, Aeree Cho, Haorang Wang, Matthew Lau, Wenke Lee, Wilian Lunardi, Martin Andreoni, Duen Horng Chau
arXiv:2606.14504v2 Announce Type: replace
Abstract: Physical adversarial attacks on vision systems are typically studied via scene manipulation, such as adversarial patches or projections. A smaller...
By Qinlin He (Brian), Zeming Zhuang (Brian), Yongji Wu (Brian), Lan Zhang (Brian), Xiaoyong (Brian), Yuan
arXiv:2609.14377v1 Announce Type: new
Abstract: Camouflage image generation (CIG) aims to synthesize realistic camouflaged images by blending foreground objects into concealment-compatible background...
By Haodong Yang, Zhongling Huang, Gong Cheng
arXiv:2610.08331v1 Announce Type: cross
Abstract: The rapid integration of Vision Language Models (VLMs) into sensitive systems introduces critical safety vulnerabilities that remain unexplored in ex...
By Heyam Bin Jahlan Areej Alhothali Abeer Alhothali