Physical Adversarial Attacks

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 50

All topics

Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies
Jun 9, 2026Zi Yin, Peilin Chai, Siyuan Huang +1Adversarial Attacks Diffusion Policy
Tsinghua University · Independent Researcher · Johns Hopkins University +1
Partially Observable Adversarial Patch Attacks on Vision-Language-Action Models in Robotics
Jun 2, 2026Xiaofei Wang, Mingliang Han, Tianyu Hao +3VLM Robustness Adversarial Patch Attacks
Department of Automation, University of Science and Technology of China, Hefei, China · SmartMore Corporation · Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China +2
ATLAS: A Large-Scale Evaluation Benchmark for Adversarial LiDAR Perception
Jun 1, 2026Mellon M. Zhang, Siddhant Panse, Zimo Fan +3Lidar-Based 3D Object Detection Adversarial Attacks
Georgia Institute of Technology
Digital-to-Physical Transfer of Adversarial Patches for Aerial Vehicle Detection
May 29, 2026Jung Heum Woo, Eun-Kyu LeeAdversarial Patch Attacks Adversarial Robustness
School of Information Technology Incheon National University Incheon 22012, Republic of Korea
AdvScene: Rethinking Adversarial Patch Evaluation Through Scene Robustness
May 28, 2026Xiaoyong, Yuan, Lan +1Adversarial Patch Attacks Adversarial Robustness
Brian · Clemson University · Clemson, SC, USA +1
VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking
May 27, 2026Jiyuan Fu, Kaixun Jiang, Jingkai Jia +7Adversarial Patch Attacks Adversarial Attacks on VLA Models
Fudan University · The Hong Kong Polytechnic University
Exposing Vulnerabilities in Visible-Infrared VLMs: A Unified Geometric Adversarial Framework with Cross-Task Transferability
May 21, 2026Xiang Chen, Yuxian Dong, Chao Li +6VLM Robustness Adversarial Patch Attacks
Adversarial Trust Poisoning in Vehicular Collaborative Perception
May 21, 2026Yutong Liu, Chenyi Wang, Ming F. Li +1Autonomous Driving Trust in AI
ECE Department, The University of Arizona, Tucson, AZ
Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object Detection
May 18, 2026Yixing Yong, Jian Wang, Ming Lei +2Adversarial Attacks Infrared Object Detection
School of Information and Communications Engineering, Faculty of Electronic and Information Engineering, Xi’an Jiao-tong University, Xi’an, China · School of Physics, Xi’an Jiao-tong University, Xi’an, China.
Towards Universal Physical Adversarial Attacks via a Joint Multi-Objective and Multi-Model Optimization Framework
May 18, 2026Ziyang Liu, Hongyuan Wang, Zijian Wang +4Transfer-Based Adversarial Attacks Black-Box Adversarial Attacks
Research Center for Space Optical Engineering, Harbin Institute of Technology, Harbin 150001, China · Zhengzhou Research Institute, Harbin Institute of Technology, Zhengzhou 450000, China
Still Camouflage, Moving Illusion: View-Induced Trajectory Manipulation in Autonomous Driving
May 12, 2026Shuo Ju, Qingzhao Zhang, Huashan Chen +6Adversarial Attacks Autonomous Driving Perception
Institute of Information Engineering, Chinese Academy of Sciences · The University of Arizona · Beijing Jiaotong University +1
Physical Adversarial Clothing Evades Visible-Thermal Detectors via Non-Overlapping RGB-T Pattern
May 6, 2026Xiaopei Zhu, Guanning Zeng, Zhanhao Hu +2Physical Adversarial Attacks
Department of Computer Science and Technology, BNRist, Tsinghua University · University of California Berkeley · IDG/McGovern Institute for Brain Research, Tsinghua University +1
Scale-Aware Adversarial Analysis: A Diagnostic for Generative AI in Multiscale Complex Systems
May 1, 2026Mengke Zhao, Guang-Xing Li, Duo Xu +1Generative Modeling Generative AI Evaluation
School of Astronomy and Space Science, Nanjing University, 163 Xianlin Avenue, Nanjing 210023, Jiangsu, People’s Republic of China · Key Laboratory of Modern Astronomy and Astrophysics (Nanjing University), Ministry of Education, Nanjing 210023, Jiangsu, People’s Republic of China · South-Western Institute for Astronomy Research, Yunnan University, Kunming 650091, People’s Republic of China +1
Understanding Adversarial Transferability in Vision-Language Models for Autonomous Driving: A Cross-Architecture Analysis
Apr 30, 2026David Fernandez, Pedram MohajerAnsari, Amir Salarpour +1Adversarial Attacks on VLMs Vision-Language Models
School of Computing, Clemson University, USA
The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches
Apr 29, 2026Vishesh Kumar, Akshay AgarwalAdversarial Patch Attacks OOD Detection
Trustworthy BiometraVision Lab, Indian Institute of Science Education and Research Bhopal, India
Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving
Apr 25, 2026Zihui Zhu, Ziqi Zhou, Yichen Wang +3Adversarial Patch Attacks Autonomous Driving Perception
Huazhong University of Science and Technology
Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models
Apr 24, 2026Shihui Yan, Ziqi Zhou, Yufei Song +3Adversarial Patch Attacks Transfer-Based Adversarial Attacks
Huazhong University of Science and Technology China
Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classification
Apr 16, 2026Weiwei Zhuang, Wangze Xie, Qi Zhang +9Remote Sensing Image Understanding Transfer-Based Adversarial Attacks
School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, 361000, China · Faculty of Data Science, City University of Macau, Macau SAR, China · Dundee International Institute, Central South University, Changsha, China +7
UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks
Oct 19, 2025Mansi Phute, Matthew Hull, Haoran Wang +6Adversarial Attacks Adversarial Perturbations
Georgia Institute of Technology, USA · Technology Innovation Institute, UAE
A Simulation Framework for Electromagnetic Signal Injection Attacks on Image Sensors
Aug 9, 2024Youqian Zhang, MK Michael Cheung, Chunxi Yang +6Adversarial Robustness Physical Adversarial Attacks
The Hong Kong Polytechnic University, Hong Kong · The Education University of Hong Kong, Hong Kong · Simon Fraser University, Canada

Jun 9, 2026, cs.ROJ/K move · Enter open · S save

Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies

Zi Yin, Peilin Chai, Siyuan Huang, Zhanhao Hu

Tsinghua University · Independent Researcher · Johns Hopkins University+1

Adversarial Attacks Diffusion Policy Adversarial Perturbations Physical Adversarial Attacks

Open paper AskPDF arXiv

Diffusion-based action generation has become a foundational component of embodied AI, but its reliance on visual conditioning leaves deployed visuomotor policies vulnerable to adversarial manipulation. Most prior attacks focus on disruption: they perturb the observation stream to reduce task success or induce erratic behavior. We study a stronger threat, Test-time Adversarial Takeover (TAKO), in which an attacker obtains a real-time steering interface over a frozen robot policy and turns it into a remotely piloted instrument. TAKO learns a small vocabulary of reusable universal patches through differentiable diffusion inference; at test time, the attacker switches among these patches in the camera stream to compose attacker-chosen trajectories. This works because the perturbation acts on the visual conditioning pathway, where the induced bias can persist through iterative generative inference. We further show that the natural targeted baseline, target-policy matching, fails because the victim policy cannot reliably supervise itself on out-of-distribution target shifts. Across four tasks (2D manipulation, simulated aerial delivery, simulated ground navigation, and physical-world ground navigation), two visual encoders (ResNet-18 and EfficientNet-B0 + Transformer), and three generative inference families (DDPM, DDIM, and flow matching), human operators achieve 100% takeover success on attacker-defined objectives in every evaluated setting. The project page is available at https://tako-attack.github.io.

Momentum

Related topics

Latest papers 50