arXiv · 2611.18702
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%.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Jinquan Zhang, Run Yang, Dongfu Yin, Qiang Lai, Yufeng Yan, Pengshuai Yin, F. Richard Yu. 2026-11-06. Robustness as a Transferable Skill: Cross-Task Adversarial Defense for Vision-Language-Action Policies. https://searcharxiv.com/abs/2611.18702
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.