让视觉语言动作模型按设定方式出错，且难以察觉。
TrapVLA: Trapping Vision-Language-Action Models in Configured Failure Modes
- 用隐蔽文本触发控制机器人失败模式
- 可精准诱导指定位置偏移等四类故障
- 适合研究机器人安全与后门攻击防御
本文提出配置失败陷阱（Configured Failure Trapping），一种针对视觉-语言-动作（VLA）模型的新式后门攻击任务。该攻击通过隐蔽文本触发，诱导机器人进入预设的故障模式，如特定位置偏移抓取，而非任意失败。不同于以往攻击只要求任务失败即成功，此任务要求攻击者精确控制失败形式，更具挑战性且更难检测。为此，我们设计了高质量目标轨迹合成的数据引擎和自动化的故障保真度评估工具，并构建了两个新基准：Trap-LIBERO 和 Trap-RoboTwin，覆盖四种典型故障模式。针对稀疏动作偏差这一核心挑战，提出 TrapVLA 方法，显式学习触发引起的动作残差，引导策略走向预设故障行为。在仿真与真实机器人场景中的大量实验表明，TrapVLA 能有效注入配置化故障，同时保持对干净数据的高性能。
原文摘要 · Abstract (English)
This work introduces Configured Failure Trapping, a novel backdoor attack task against Vision-Language-Action (VLA) models, which aims to activate attacks through stealthy textual triggers and induce configured failure modes. Unlike prior backdoor attacks that treat any task failure as a successful attack, Configured Failure Trapping requires the attacker to control how the robot fails (e.g., causing the robot to grasp with a specified positional offset), making it substantially more challenging and hard to detect. To support the new task, we propose an effective data engine for synthesizing high-quality target trajectories and an automated suite for measuring configured-failure fidelity. Then, based on this foundation, we construct two new benchmarks, namely Trap-LIBERO and Trap-RoboTwin, that instantiate Configured Failure Trapping across four representative failure modes. To address this task, we identify sparse action deviation as a critical challenge and accordingly propose a novel method named TrapVLA, which explicitly learns trigger-induced action residuals to steer the policy toward the configured failure behavior. Extensive experiments across simulation benchmarks and real-world robotic settings show that TrapVLA effectively injects configured failure modes into VLA models while largely preserving performance on clean data. Project page: https://john-liua.github.io/TrapVLA/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。