VLALeaks: Membership Inference Attacks against Vision-Language-Action Models

Computer Science > Cryptography and Security [Submitted on 13 Jun 2026] VLALeaks: Membership Inference Attacks against Vision-Language-Action Models Xukun Luan, Jinyan Liu, Xuesong Li, Yuanguo Bi, Renjun Wu, Zhongxiang Lei, Di Wang 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. Comments: Security and Privacy Subjects: Cryptography and Security (cs.CR); Robotics (cs.RO) Cite as: arXiv:2606.15165 [cs.CR]   (or arXiv:2606.15165v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.15165 Focus to learn more Submission history From: Xukun Luan [view email] [v1] Sat, 13 Jun 2026 07:29:33 UTC (15,157 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.RO References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)