On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations

• URL: http://arxiv.org/abs/2510.00037v3
• Date: Tue, 28 Oct 2025 09:55:21 GMT
• Title: On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
• Abstract summary: In vision-language-action (VLA) models, robustness to real-world perturbations is critical for deployment.<n>We propose RobustVLA against perturbations in VLA inputs and outputs.<n> Experiments on LIBERO demonstrate our RobustVLA delivers absolute gains over baselines of 12.6% on the pi0 backbone and 10.4% on the OpenVLA backbone.
• Score: 52.1029745126386
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In Vision-Language-Action (VLA) models, robustness to real-world perturbations is critical for deployment. Existing methods target simple visual disturbances, overlooking the broader multi-modal perturbations that arise in actions, instructions, environments, and observations. Here, we first evaluate the robustness of mainstream VLAs under 17 perturbations across four modalities. We find (1) actions as the most fragile modality, (2) Existing visual-robust VLA do not gain robustness in other modality, and (3) pi0 demonstrates superior robustness with a diffusion-based action head. To build multi-modal robust VLAs, we propose RobustVLA against perturbations in VLA inputs and outputs. For output robustness, we perform offline robust optimization against worst-case action noise that maximizes mismatch in flow matching objective. This can be seen as adversarial training, label smoothing, and outlier penalization. For input robustness, we enforce consistent actions across input variations that preserve task semantics. To account for multiple perturbations, we formulate robustness as a multi-armed bandit problem and apply an upper confidence bound algorithm to automatically identify the most harmful noise. Experiments on LIBERO demonstrate our RobustVLA delivers absolute gains over baselines of 12.6% on the pi0 backbone and 10.4% on the OpenVLA backbone across all 17 perturbations, achieving 50.6x faster inference than existing visual-robust VLAs, and a 10.4% gain under mixed perturbations. Our RobustVLA is particularly effective on real-world FR5 robot with limited demonstrations, showing absolute gains by 65.6% under perturbations of four modalities.

Related papers

• STRONG-VLA: Decoupled Robustness Learning for Vision-Language-Action Models under Multimodal Perturbations [26.063335767640083]
  We propose STRONG-VLA, a decoupled fine-tuning framework for Vision-Language-Action (VLA) models.<n>In Stage I, the model is exposed to a curriculum of multimodal perturbations with increasing difficulty.<n>In Stage II, the model is re-aligned with clean task distributions to recover execution fidelity while preserving robustness.<n>Experiments on the LIBERO benchmark show that STRONG-VLA consistently improves task success rates across multiple VLA architectures.
  arXiv  Detail & Related papers  (2026-04-11T06:37:47Z)
• Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation [95.89924101984566]
  We introduce OptimusVLA, a dual-memory VLA framework with Global Prior Memory (GPM) and Local Consistency Memory (LCM)<n>GPM replaces Gaussian noise with task-level priors retrieved from semantically similar trajectories.<n>LCM injects a learned consistency constraint that enforces temporal coherence and smoothness of trajectory.
  arXiv  Detail & Related papers  (2026-02-22T15:39:34Z)
• $\mathcal{E}_0$: Enhancing Generalization and Fine-Grained Control in VLA Models via Continuized Discrete Diffusion [65.77755100137728]
  We introduce E0, a continuized discrete diffusion framework that formulates action generation as iterative denoising over quantized action tokens.<n>E0 achieves state-of-the-art performance across 14 diverse environments, outperforming strong baselines by 10.7% on average.
  arXiv  Detail & Related papers  (2025-11-26T16:14:20Z)
• When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Models [75.16145284285456]
  We introduce VLA-Fool, a comprehensive study of multimodal adversarial robustness in embodied VLA models under both white-box and black-box settings.<n>We develop the first automatically crafted and semantically guided prompting framework.<n> Experiments on the LIBERO benchmark reveal that even minor multimodal perturbations can cause significant behavioral deviations.
  arXiv  Detail & Related papers  (2025-11-20T10:14:32Z)
• EvoVLA: Self-Evolving Vision-Language-Action Model [11.746804244345613]
  Long-horizon robotic manipulation remains challenging for Vision-Language-Action (VLA) models.<n>We present EvoVLA, a self-supervised VLA framework that addresses this issue through three complementary components.<n>EvoVLA achieves one-and-a-half times better sample efficiency and reduces stage hallucination from 38.5 percent to 14.8 percent.
  arXiv  Detail & Related papers  (2025-11-20T09:08:33Z)
• DUAL-Bench: Measuring Over-Refusal and Robustness in Vision-Language Models [59.45605332033458]
  Safety mechanisms can backfire, causing over-refusal, where models decline benign requests out of excessive caution.<n>No existing benchmark has systematically addressed over-refusal in the visual modality.<n>This setting introduces unique challenges, such as dual-use cases where an instruction is harmless, but the accompanying image contains harmful content.
  arXiv  Detail & Related papers  (2025-10-12T23:21:34Z)
• dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought [66.78110237549087]
  Vision-Language-Action (VLA) models are emerging as a next-generation paradigm for robotics.<n>We introduce dVLA, a diffusion-based VLA that unifies visual perception, language reasoning, and robotic control in a single system.
  arXiv  Detail & Related papers  (2025-09-30T02:36:11Z)
• DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models [50.21378052667732]
  We conduct an in-depth analysis of dLLM vulnerabilities to jailbreak attacks across two distinct dimensions: intra-step and inter-step dynamics.<n>We propose DiffuGuard, a training-free defense framework that addresses vulnerabilities through a dual-stage approach.
  arXiv  Detail & Related papers  (2025-09-29T05:17:10Z)
• FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models [124.02734355214325]
  Vision-Language-Action (VLA) models are driving rapid progress in robotics.<n> adversarial images can "freeze" VLA models and cause them to ignore subsequent instructions.<n>FreezeVLA generates and evaluates action-freezing attacks via min-max bi-level optimization.
  arXiv  Detail & Related papers  (2025-09-24T08:15:28Z)
• To Trust Or Not To Trust Your Vision-Language Model's Prediction [32.26134619728882]
  We introduce TrustVLM, a training-free framework designed to address the challenge of estimating when VLM's predictions can be trusted.<n>Motivated by the observed modality gap in VLMs, we propose a novel confidence-scoring function that leverages this space to improve misclassification detection.<n>We rigorously evaluate our approach across 17 diverse datasets, employing 4 architectures and 2 VLMs, and demonstrate state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-05-29T17:59:01Z)
• Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks [10.44351773183656]
  Vision-Language Models (VLMs) are vulnerable to jailbreak attacks when processing noisy or corrupted images.<n>To address this challenge, we propose Robust-VLGuard, a multimodal safety dataset aligned with misaligned image-text pairs.<n>For stronger optimization-based visual perturbation attacks, we propose DiffPure-VLM, leveraging diffusion models to convert adversarial perturbations into Gaussian-like noise.
  arXiv  Detail & Related papers  (2025-04-02T02:35:19Z)
• VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models [66.56298924208319]
  Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems.<n>Current assessment methods primarily rely on AI-annotated preference labels from traditional tasks.<n>We introduce VL-RewardBench, a comprehensive benchmark spanning general multimodal queries, visual hallucination detection, and complex reasoning tasks.
  arXiv  Detail & Related papers  (2024-11-26T14:08:34Z)
• RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness [102.06442250444618]
  We introduce RLAIF-V, a novel framework that aligns MLLMs in a fully open-source paradigm.<n> RLAIF-V maximally explores open-source MLLMs from two perspectives, including high-quality feedback data generation.<n>Experiments on six benchmarks in both automatic and human evaluation show that RLAIF-V substantially enhances the trustworthiness of models.
  arXiv  Detail & Related papers  (2024-05-27T14:37:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.