Adversarial Attacks on VLA Models

VLA: Vision-Language-Action

Vision-language-action models turn camera observations and natural-language instructions into robot actions, so adversarial-attack research asks how small or hidden changes can derail grounding, planning, or control in embodied settings. Studies probe instruction edits and image perturbations, physical patches and textures, training-time backdoors, and faults in model weights or intermediate reasoning. Evaluations span manipulation simulators such as LIBERO, autonomous-driving scenarios, and real robot hardware; defenses include robust fine-tuning, runtime monitoring and recovery, and certified action or rollout guarantees. Work increasingly examines transferable, long-horizon, and adaptive threats, while a central challenge is improving robustness without sacrificing task-relevant perception or clean-task performance.

Latest papers

32 papers3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Enhancing Visual Task-Redirection Attacks on Vision-Language-Action Models via Closed-Loop Optimization
Oct 16, 2026Chunjin Ye, Guanying Chen, Jianjie Huang +6Adversarial Attacks on VLA Models Adversarial Attacks
Sun Yat-sen University, Shenzhen 518107, China · Zhongguancun Academy, Beijing 100094, China · Wuhan University, Wuhan 430072, China +3
Red-Teaming of Vision-Language-Action Models via Quality Diversity Environment Generation
Oct 10, 2026Shihan Zhao, Henry Chen, Ya-Chuan Hsu +7Robustness of VLA Models Adversarial Attacks on VLA Models
Thomas Lord Department of Computer Science, University of Southern California. · Columbia University. · Adobe Research +1
Exploiting Vulnerabilities: Universal Adversarial Attacks on Vision-Language-Action Models in Robotics
Sep 30, 2026Songhua Yang, Ziyu Liu, Yuanwei Liu +5Adversarial Attacks on VLA Models Robotic Manipulation
School of Computer Science, Wuhan University. · School of Robotics, Wuhan University. · School of Power and Mechanical Engineering, Wuhan University.
Beyond Patch Removal: Persistent Adversarial Effects in Vision-Language-Action Policies
Sep 17, 2026Enhao Wu, Fusen Guo, Yuxin Cao +3Adversarial Patch Attacks Adversarial Attacks on VLA Models
UNSW Sydney, Australia · UNSW Canberra, Australia · National University of Singapore, Singapore +2
TrapVLA: Trapping Vision-Language-Action Models in Configured Failure Modes
Aug 27, 2026Jun-Hui Liu, Kun-Yu Lin, Yi-Lin Wei +9Backdoor Attacks on VLA Models Adversarial Attacks on VLA Models
School of Computer Science and Engineering, Sun Yat-sen University, China · Pengcheng Laboratory, China · The University of Hong Kong, China +1
CertVLA: Certified Defense against Physical Visual Attacks for Vision-Language-Action Models
Aug 21, 2026Hui Lu, Zhijie Peng, Yuqi Lin +8Robustness of VLA Models Adversarial Attacks on VLA Models
Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability
Aug 16, 2026Yudong Gao, Linghan Chen, Wenhan Wu +5Adversarial Attacks Adversarial Attacks on VLA Models
The Hong Kong University of Science and Technology · Adelaide University · Wuhan University +3
UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models
Aug 13, 2026Yukun Dai, Mingzhe Dai, Tianshi Wang +3Adversarial Attacks on VLA Models Vision-Language-Action Models
Tongji University · Mohamed bin Zayed University of Artificial Intelligence · University of Electronic Science and Technology of China
Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models
Aug 11, 2026Jiahui Han, Yuhui Yao, Xin Wang +6Adversarial Attacks Adversarial Attacks on VLA Models
1Xi’an Jiaotong University · 2Shanghai AI Laboratory · University of Science and Technology of China
Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking
Aug 4, 2026Jinquan Zhang, Dongfu Yin, Run Yang +3Fine-Tuning Language-Conditioned Robot Manipulation
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China · Shenzhen University, Shenzhen, China · Carleton University, Ottawa, Canada
DRIFT: Derailing Denoising Trajectories of Flow-Matching VLAs with Adversarial Patch Attack
Aug 4, 2026Hoseong Tae, Jong-Seok LeeAdversarial Patch Attacks Adversarial Attacks on VLA Models
School of Integrated Technology, Yonsei University
VLAGuard: A Framework for Evaluating and Mitigating Physical Attention Hijacking in Vision-Language-Action Robots within Wireless Sensor Networks
Aug 2, 2026Dongfu Yin, Jinquan ZhangAdversarial Patch Attacks Adversarial Attacks on VLA Models
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China · Shenzhen University, Shenzhen, China
Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models
Jul 20, 2026Tuan Duong Trinh, Naveed Akhtar, Basim AzamNeural Network Robustness Adversarial Attacks on VLA Models
University of Melbourne Parkville, VIC, Australia
Lights, Camera, Malfunction: When Illumination Robustness Leaves VLA Models Blind to Color
Jul 16, 2026Marino Watanabe, Takami Sato, Kentaro YoshiokaAdversarial Training Adversarial Attacks
Keio University
TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors
Jul 14, 2026Pinhan Fu, Xianda Guo, Xuetao Li +5Adversarial Attacks on VLA Models Vision-Language-Action Models
School of Computer Science, Wuhan University · Institute of Automation, Chinese Academy of Sciences · 3HUST +1
Technical Report on the CVPR 2026@AdvML Workshop Challenge
Jul 13, 2026Tianyuan Zhang, Zonglei Jing, Jiangfan Liu +47VLMs for Autonomous Driving Adversarial Attacks on VLA Models
!Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics
Jul 5, 2026Stefan Bühler, Mark SchuteraNeural Network Robustness Adversarial Attacks on VLA Models
Independent Researcher · Duale Hochschule Baden-Württemberg, Ravensburg
Attacking the Trusted Imagination: Oracle-Level Integrity Attacks on Imagine-then-Act World Models
Jun 22, 2026Linghan Chen, Kaiyan Ji, Minyu GuoAdversarial Attacks on World Models Adversarial Attacks
Adelaide University
Trajectory-Level Redirection Attacks on Vision-Language-Action Models
Jun 11, 2026Gokul Puthumanaillam, Vardhan Dongre, Pranay Thangeda +3Language-Conditioned Robot Manipulation Adversarial Attacks on VLA Models
University of Illinois Urbana-Champaign · Amazon
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
ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving
May 27, 2026Mohammadreza Teymoorianfard, Jean-Philippe Monteuuis, Jonathan Petit +1VLMs for Autonomous Driving Autonomous Driving Safety Evaluation
University of Massachusetts Amherst · Qualcomm
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
Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models
May 25, 2026Jianwei TaiNeural Network Robustness Adversarial Robustness
School of Internet, Anhui University
ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models
May 9, 2026Kewei Chen, Yayu Long, Shuai Li +1Adversarial Attacks Adversarial Attacks on VLA Models
Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences · Chongqing School, University of Chinese Academy of Sciences · Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
Apr 26, 2026Qi Li, Bo Yin, Weiqi Huang +6AI Agent Safety Adversarial Attacks on VLA Models
National University of Singapore · Peking University · Monash University
RedVLA: Physical Red Teaming for Vision-Language-Action Models
Apr 24, 2026Yuhao Zhang, Borong Zhang, Jiaming Fan +4Robotics Adversarial Attacks on VLA Models
Institute for AI, Peking University · State Key Laboratory of General Artificial Intelligence, Peking University
Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming
Apr 7, 2026Baoshun Tong, Haoran He, Ling Pan +2Adversarial Attacks on VLA Models Robustness of VLA Models
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China · The Hong Kong University of Science and Technology, Hong Kong SAR, China
Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models
Apr 2, 2026Jiawei Chen, Simin Huang, Jiawei Du +5Adversarial Attacks on VLA Models Adversarial Examples
East China Normal University · Zhongguancun Academy · CFAR, A*STAR, Singapore +2
SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models
Mar 26, 2026Xiyang Wu, Guangyao Shi, Qingzi Wang +3Adversarial Attacks on VLA Models Robustness of VLA Models
University of Maryland, College Park, MD, USA · University of Southern California, Los Angeles, CA, USA · University of Central Florida, Orlando, FL, USA
TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches
Mar 24, 2026Zhengxian Huang, Wenjun Zhu, Haoxuan Qiu +2Adversarial Attacks on VLA Models Robustness of VLA Models
Zhejiang University, Hangzhou, China · Harbin Institute of Technology, Harbin, China

Oct 16, 2026J/K move · Enter open · S save

Enhancing Visual Task-Redirection Attacks on Vision-Language-Action Models via Closed-Loop Optimization

Chunjin Ye, Guanying Chen, Jianjie Huang, Jianhao Chen+5

Sun Yat-sen University, Shenzhen 518107, China · Zhongguancun Academy, Beijing 100094, China · Wuhan University, Wuhan 430072, China+3

Adversarial Attacks on VLA Models Adversarial Attacks Robustness of VLA Models

Open paper AskPDF arXiv

Vision-language-action (VLA) models enable language-guided robot manipulation, but remain vulnerable to visual attacks that undermine user control over robot behavior. Prior studies optimize visual perturbations using fixed target supervision. However, the perturbation can change earlier actions and, in turn, the physical states reached later. As the attacked trajectory evolves, this supervision may no longer match the behavior needed at the states actually reached. Accurately matching these targets can therefore fail to advance the attacker-specified task. Even with suitable supervision, reducing average matching error does not ensure sustained task progress. The robot may still fail at a critical stage, and further updates can disrupt previously successful behavior. To address these limitations, we propose TRACO, a framework that enhances existing targeted visual attacks through closed-loop optimization. Its Execution-Driven Supervision rebuilds supervision for the states reached under attack to guide subsequent updates. Within this framework, Progress-Guided Selection focuses updates where progress stalls while maintaining supervision on the earlier behavior needed to reach that point. Experiments across VLA models and simulation environments show improved task-redirection success with TRACO, highlighting the security implications of closed-loop attack optimization.