概念ベース辞書学習によるVLAモデルの推論時安全性制御
Concept-Based Dictionary Learning for Inference-Time Safety in Vision Language Action Models
VLAモデルの隠れ層活性からスパースで解釈可能な辞書を学習し、有害な概念方向を検出・抑制することで、再学習なしに推論時の安全性を高める手法を提案。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Siqi Wen, Shu Yang, Shaopeng Fu, Jingfeng Zhang, Lijie Hu, Di Wang
分類: cs.RO
原文アブストラクト
Vision Language Action (VLA) models close the perception action loop by translating multimodal instructions into executable behaviors, but this very capability magnifies safety risks: jailbreaks that merely yield toxic text in LLMs can trigger unsafe physical actions in embodied systems. Existing defenses alignment, filtering, or prompt hardening intervene too late or at the wrong modality, leaving fused representations exploitable. We introduce a concept based dictionary learning framework for inference time safety control. By learning sparse, interpretable dictionaries from hidden activations, our method identifies harmful concept directions and attenuates risky components when the estimated risk exceeds a threshold. Experiments on Libero-Harm, BadRobot, RoboPair, and IS-Bench show that our approach achieves state-of-the-art defense performance, cutting attack success rates by over 70\% while maintaining task success. Crucially, the framework is plug-in and model-agnostic, requiring no retraining and integrating seamlessly with diverse VLAs. To our knowledge, this is the first inference time concept based safety method for embodied systems, advancing both interpretability and safe deployment of VLA models.
