mlsanityData to 7 Oct 2026

VLAGuard: A Framework for Evaluating and Mitigating Physical Attention Hijacking in Vision-Language-Action Robots within Wireless Sensor Networks

arXiv 2608.01028 ↗First posted 2 Aug 2026cs.RO cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Deploying Vision-Language-Action (VLA) robots as mobile edge nodes within wireless sensor networks (WSNs) requires robust protection against physical adversarial threats. We present VLAGuard, a framework to assess and mitigate a critical vulnerability: policy-critical action-to-vision attention hijacking. We first introduce a stress-test module, Visuomotor Attention-guided Semantic Attack (VASA), using printable patches to severely distract the robot's action-conditioned cross-attention. To counter this, we propose Attention-Protective Fine-Tuning (APFT), a defense that stabilizes spatiotemporal attention and enforces geometric consistency with zero inference overhead. Evaluations across simulated and physical WSN-assisted smart environments demonstrate significant robustness gains. APFT reduces the OpenVLA failure rate from 100.0% to 25.9% in LIBERO simulations. Furthermore, across 2,000 real-world trials, APFT improves the average success rate from 23.0% to 67.4% under severe patch attacks. This highlights that protecting attention pathways is important for improving the robustness of VLA-driven edge nodes in sensor networks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 41 references that are in the map. First posted on arXiv 2 Aug 2026.

Builds on

35 of 41 references.

References · 35

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  5. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  6. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  7. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  8. 2016Learning without Forgettingcited by 2,465
  9. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  10. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  11. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  12. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
23 more
  1. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  2. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  3. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  4. 2024Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Surveycited by 641
  5. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  6. 2017Adversarial Patchcited by 514
  7. 2022Diffusion Models for Adversarial Purificationcited by 469
  8. 2024Jailbreak Vision Language Models via Bi-Modal Adversarial Promptcited by 103
  9. 2024Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Roboticscited by 68
  10. 2025BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimizationcited by 37
  11. 2025Adversarial Attacks on Robotic Vision Language Action Modelscited by 31
  12. 2024EventGPT: Event Stream Understanding with Multimodal Large Language Modelscited by 27
  13. 2025Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variationscited by 24
  14. 2025FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Modelscited by 19
  15. 2025Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Modelscited by 19
  16. 2024Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injectioncited by 17
  17. 2024Manipulation Facing Threats: Evaluating Physical Vulnerabilities in End-to-End Vision Language Action Modelscited by 16
  18. 2025Goal-oriented Backdoor Attack against Vision-Language-Action Models via Physical Objectscited by 16
  19. 2025When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Modelscited by 16
  20. 2025PVChat: Personalized Video Chat with One-Shot Learningcited by 13
  21. 2025AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Modelscited by 10
  22. 2025When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Modelscited by 9
  23. 2025Attention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Modelscited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking
  2. 2025Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attacks
  3. 2026VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking
  4. 2026Partially Observable Adversarial Patch Attacks on Vision-Language-Action Models in Robotics
  5. 2026Hijacking Robots with a Piece of Paper: A Systematic Study of Physical Prompt Injection in VLM-Controlled Robots
  6. 2026When Attention Betrays: Erasing Backdoor Attacks in Robotic Policies by Reconstructing Visual Tokens
  7. 2026Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models
  8. 2026SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models