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: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:2608. 07750v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) have found successful deployment in numerous vision perception systems.
By Cong Chen, Jean-Philippe Monteuuis, Jonathan Petit
arXiv:2608.20748v1 Announce Type: new
Abstract: The Visual Geometry Grounded Transformer (VGGT) enables unified feed-forward 3D reconstruction from multi-view images. However, deploying such a high-p...
By Qi Song, Ziyuan Luo, Haoliang Han, Renjie Wan
arXiv:2610.41834v1 Announce Type: new
Abstract: Accurate BEV map prediction is a critical component of autonomous driving systems, enabling downstream planning and control. Recent approaches such as...
By Christian Bohn, Harsh Yadav, Klaus Friedrichs, Hasan Tercan, Tobias Meisen
arXiv:2609.18133v1 Announce Type: new
Abstract: Visible-infrared object detectors are used for robust perception under challenging illumination and weather conditions. Current physical attacks apply...
By Yueqi Zhu, Qi Ming, Guo Cheng, Yongkang Zhang, Feiran Liu, Juan Fang, Jiahuan Zhou, Jiangmeng Li, Yuhan Zhang
The paper presents 3DGAA, a fabrication-first framework that generates view-consistent, geometry-preserving adversarial wraps for vehicles using 3D Gaussian splatting optimization. It ensures consistency across viewpoints, illumination, and occlusion while limiting changes to vehicle geometry, producing realistic print-only textures that significantly reduce detection confidence and average precision in simulations and physical tests. Ablation and efficiency studies analyze the impact of physical filtering, augmentation, and shape-consistency regularization, and the method demonstrates robustness against common preprocessing defenses and cross-detector transferability.
By Yixun Zhang, Lizhi Wang, Junjun Zhao, Wending Zhao, Feng Zhou, Yonghao Dang, Jianqin Yin
arXiv:2609.17856v1 Announce Type: new
Abstract: Heterogeneous cooperative perception (CP) enables connected vehicles with diverse sensor setups to share spatial awareness via compact feature maps, wh...
By Chenyi Wang, Yutong Liu, Qingzhao Zhang, Ming F. Li
arXiv:2510. 16923v3 Announce Type: replace-cross Abstract: Deep learning models deployed in safety critical applications like autonomous driving use simulations to test their robustness against adversarial attacks in realistic conditions.
By Mansi Phute, Matthew Hull, Haoran Wang, Alec Helbling, ShengYun Peng, Willian Lunardi, Martin Andreoni, Wenke Lee, Duen Horng Chau
arXiv:2603.11521v2 Announce Type: replace-cross
Abstract: Unsupervised Camouflaged Object Detection (UCOD) remains a challenging task due to the high intrinsic similarity between target objects and t...
By Shuo Jiang, Gaojia Zhang, Min Tan, Yufei Yin, Gang Pan
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
Camera-based object detectors are vulnerable to physical adversarial attacks designed to suppress detections. While adversarial training and input purification offer some protection, they often overfit to specific attack distributions and fail on adaptive adversaries.