# Explainable Adversarial-Robust Vision-Language-Action Model for Robotic Manipulation

arXiv: https://arxiv.org/abs/2512.11865 · HTML: https://mlsanity.com/paper/2512.11865/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Safety and adversarial attacks, one of 13 directions in Vision-language-action models.
- Builds on 0 of its 1 references that are in the map.
- First posted on arXiv 5 Dec 2025.

## Placed in

- Vision-language-action models / [Safety and adversarial attacks](https://mlsanity.com/vla/safety-and-adversarial-attacks/)

## Built on by (most cited first, 1 of 1)

- [Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models](https://mlsanity.com/paper/2605.25889/) (2026)

## Abstract (arXiv)

Smart farming has emerged as a key technology for advancing modern agriculture through automation and intelligent control. However, systems relying on RGB cameras for perception and robotic manipulators for control, common in smart farming, are vulnerable to photometric perturbations such as hue, illumination, and noise changes, which can cause malfunction under adversarial attacks. To address this issue, we propose an explainable adversarial-robust Vision-Language-Action model based on the OpenVLA-OFT framework. The model integrates an Evidence-3 module that detects photometric perturbations and generates natural language explanations of their causes and effects. Experiments show that the proposed model reduces Current Action L1 loss by 21.7% and Next Actions L1 loss by 18.4% compared to the baseline, demonstrating improved action prediction accuracy and explainability under adversarial conditions.