通过多模态领域适应预防机器人越狱
Preventing Robotic Jailbreaking via Multimodal Domain Adaptation
AI总结：
针对机器人场景中越狱检测数据稀缺、跨域泛化不足的问题，提出 J-DAPT 多模态领域适应框架，融合文本与视觉嵌入并对齐领域数据，在三类机器人任务中以极小开销实现接近100%的检测准确率。
摘要：
大语言模型（LLM）和视觉语言模型（VLM）正越来越多地部署于机器人环境中，但仍易受越狱攻击；这类攻击会绕过安全机制，并在现实世界中诱发不安全或造成物理伤害的行为。越狱分类器等数据驱动防御展现出良好前景，但在专用数据集稀缺的领域中难以泛化，从而限制了其在机器人及其他安全关键场景中的有效性。为弥补这一差距，我们提出 J-DAPT，这是一个通过基于注意力的融合和领域适应实现多模态越狱检测的轻量级框架。J-DAPT 整合文本与视觉嵌入，以同时捕捉语义意图和环境落地信息，并将通用越狱数据集与特定领域参考数据对齐。跨自动驾驶、海事机器人和四足机器人导航的评估表明，J-DAPT 以极小开销将检测准确率提升至接近 100%。这些结果证明，J-DAPT 为保障机器人应用中的 VLM 安全提供了一种实用防御。补充材料可在 https://j-dapt.github.io 获取。
英文摘要：
Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly deployed in robotic environments but remain vulnerable to jailbreaking attacks that bypass safety mechanisms and drive unsafe or physically harmful behaviors in the real world. Data-driven defenses such as jailbreak classifiers show promise, yet they struggle to generalize in domains where specialized datasets are scarce, limiting their effectiveness in robotics and other safety-critical contexts. To address this gap, we introduce J-DAPT, a lightweight framework for multimodal jailbreak detection through attention-based fusion and domain adaptation. J-DAPT integrates textual and visual embeddings to capture both semantic intent and environmental grounding, while aligning general-purpose jailbreak datasets with domain-specific reference data. Evaluations across autonomous driving, maritime robotics, and quadruped navigation show that J-DAPT boosts detection accuracy to nearly 100% with minimal overhead. These results demonstrate that J-DAPT provides a practical defense for securing VLMs in robotic applications. Additional materials are made available at: https://j-dapt.github.io.
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。
