Newshot

Robustness as a Transferable Skill: Cross-Task Adversarial Defense for Vision-Language-Action Policies

Summary

arXiv:2611.18702v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies are vulnerable to adversarial visual perturbations, while defenses often require task-specific adversarial fine-tuning. We investigate whether robustness learned on source manipulation tasks can protect independently specialized target policies without target-side adversarial training. We first show that even a single source defense update improves robustness on held-out tasks, establishing cross-task defense reuse independently of multi-source aggregation. To combine source updates, we introduce Source-Norm Transferable Robustness Vector (SN-TRV), which retains the direction of their mean while calibrating its magnitude using source-update norms. The resulting update is applied to the target visual encoder without target adversarial data, target-side gradient optimization, or additional inference modules. Evaluations across three VLA backbones, fixed and adaptive attacks, and different source defense…

Original text(via arXiv cs.RO)

Computer Science > Robotics

Title:Robustness as a Transferable Skill: Cross-Task Adversarial Defense for Vision-Language-Action Policies

Abstract:Vision-Language-Action (VLA) policies are vulnerable to adversarial visual perturbations, while defenses often require task-specific adversarial fine-tuning. We investigate whether robustness learned on source manipulation tasks can protect independently specialized target policies without target-side adversarial training. We first show that even a single source defense update improves robustness on held-out tasks, establishing cross-task defense reuse independently of multi-source aggregation. To combine source updates, we introduce Source-Norm Transferable Robustness Vector (SN-TRV), which retains the direction of their mean while calibrating its magnitude using source-update norms. The resulting update is applied to the target visual encoder without target adversarial data, target-side gradient optimization, or additional inference modules. Evaluations across three VLA backbones, fixed and adaptive attacks, and different source defense recipes show improved robustness over naive averaging and identify limits in attack coverage. Physical PiPER trials increase average success under printed adversarial patches from 20.3% to 45.8%.
Subjects:Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV)
Cite as:arXiv:2611.18702 [cs.RO]
(or arXiv:2611.18702v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2611.18702 arXiv-issued DOI via DataCite (pending registration)

Submission history

Access Paper:

  • HTML (experimental)

Additional Features

  • Audio Summary

Current browse context:

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by arXiv cs.RO
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗