ATAAT: 視覚-言語-行動モデルに対するバックドア攻撃を防ぐ適応型脅威認識敵対的チューニングフレームワーク
ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models
視覚-言語-行動(VLA)モデルの視覚経路へのバックドア攻撃を研究し、従来手法の失敗原因である「勾配干渉」を解決する適応型フレームワークを提案した。
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: Kewei Chen, Yayu Long, Shuai Li, Mingsheng Shang
分類: cs.RO
原文アブストラクト
Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual pathway. We identify a core obstacle causing the failure of traditional attack paradigms: "Gradient Interference." This phenomenon represents an optimization failure triggered by conflicting strategies during end-to-end training. To resolve this, we propose an Adaptive Threat-Aware Adversarial Tuning (ATAAT) framework. Through its core "Threat-Method Adaptive Mapping" mechanism, ATAAT intelligently selects the optimal gradient decoupling strategy based on the adversary's capabilities. Extensive experiments demonstrate that ATAAT exhibits significant advantages, achieving a highly robust Targeted Attack Success Rate (TASR > 80%) while maintaining extreme stealthiness with merely a 5% poisoning rate. It efficiently handles complex semantic-level triggers and achieves implicit decoupled attacks in data poisoning scenarios for the first time. This work reveals a critical security vulnerability in VLAs and provides theoretical and methodological support for future defense architectures.
