面向视觉-语言-动作模型的后门基于所有权验证
Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models
AI总结：
本文提出GuardVLA，首个针对视觉-语言-动作模型的后门基于所有权验证框架，通过在训练中嵌入隐蔽无害的后门水印，实现可靠的模型所有权验证并保持正常任务性能。
摘要：
视觉-语言-动作模型（VLAs）通过使多模态输入直接生成端到端决策策略，支持通用机器人控制。随着训练后的VLAs被越来越多地共享和适应，保护模型所有权对于安全部署和负责任的开源使用至关重要。本文提出了GuardVLA，首个专门针对VLAs的后门基于所有权验证框架。GuardVLA在训练期间通过将秘密信息注入具身视觉数据中，将隐蔽且无害的后门水印嵌入受保护的模型中。在发布后验证阶段，我们提出了一种交换和检测机制，其中触发投影器和外部分类器头用于基于预测概率激活和检测嵌入的后门。在多个数据集、模型架构和适应设置上的广泛实验表明，GuardVLA能够在保持良性任务性能的同时实现可靠的模型所有权验证。进一步结果表明，嵌入的水印在发布后模型适应下仍能被检测到。
英文摘要：
Vision-Language-Action models (VLAs) support generalist robotic control by enabling end-to-end decision policies directly from multi-modal inputs. As trained VLAs are increasingly shared and adapted, protecting model ownership becomes essential for secure deployment and responsible open-source usage. In this paper, we present GuardVLA, the first backdoor-based ownership verification framework specifically designed for VLAs. GuardVLA embeds a stealthy and harmless backdoor watermark into the protected model during training by injecting secret messages into embodied visual data. For post-release verification, we propose a swap-and-detect mechanism, in which the trigger projector and an external classifier head are used to activate and detect the embedded backdoor based on prediction probabilities. Extensive experiments across multiple datasets, model architectures, and adaptation settings demonstrate that GuardVLA enables reliable ownership verification while preserving benign task performance. Further results show that the embedded watermark remains detectable under post-release model adaptation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
