Vision-Language-Action (VLA) models enable end-to-end robot control and have garnered widespread attention. However, the memorization of training data inherent to VLA, coupled with the high cost of robotic data acquisition, raises serious concerns regarding data privacy leakage and intellectual property infringement. Membership inference attacks (MIAs) aim to determine whether a given sample belongs to the training set. While representing a significant privacy threat, this attack remains underexplored in the context of VLA models. To bridge this gap, we propose VLALeaks, which is based on attention discrepancies in VLA models. We reveal, for the first time, the privacy vulnerabilities of VLA models. Specifically, it comprises a two-stage process: (1) membership feature extraction, and (2) attack model construction. Experimental results across multiple VLA benchmarks demonstrate that VLALeaks readily reveals membership information and achieves optimal attack AUC and TPR@1\%FPR, highlighting the privacy vulnerabilities in current VLA model deployments. Our work is the first systematic study of MIAs on VLA models, aiming to provide insights for secure and trustworthy VLA models.

翻译：视觉-语言-动作（VLA）模型能够实现端到端的机器人控制，并已获得广泛关注。然而，VLA模型固有的训练数据记忆特性，加之机器人数据获取的高昂成本，引发了严重的数据隐私泄露和知识产权侵权担忧。成员推理攻击（Membership Inference Attacks, MIAs）旨在判定给定样本是否属于训练集。尽管该攻击构成了重要的隐私威胁，但在VLA模型背景下研究尚不充分。为填补这一空白，我们提出VLALeaks，该方法基于VLA模型中的注意力差异。我们首次揭示了VLA模型的隐私脆弱性。具体而言，该方法包含两个阶段：（1）成员特征提取，以及（2）攻击模型构建。在多个VLA基准上的实验结果表明，VLALeaks能够轻易揭示成员信息，并在AUC和TPR@1%FPR指标上达到最优性能，凸显了当前VLA模型部署中的隐私漏洞。本文是首个针对VLA模型开展MIAs系统性研究的工作，旨在为构建安全可信的VLA模型提供洞见。