視覚言語モデルにおける深さ依存の安全幾何学:層ごとの局在化と双方向拒否制御
Depth-Dependent Safety Geometry in Vision-Language Models: Layer-Wise Localization and Bidirectional Refusal Control
凍結した視覚言語モデルの内部表現を層ごとに解析し、学習した安全方向への活性化操作で拒否応答を双方向に制御できることを示した研究。
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: Muhammad Zeeshan Karamat, Syed Talal Hassan, Christiana Chamon Garcia
分類: cs.CV, cs.CL, cs.CR, cs.LG
原文アブストラクト
Vision-Language Models (VLMs) are widely deployed, yet the internal mechanisms behind their safety behavior remain poorly understood. We present a lightweight inference-time framework for localizing and manipulating safety-sensitive representations in frozen VLMs, without retraining or modifying parameters. On Qwen3-VL-4B, layer-wise activation divergence analysis reveals non-uniform safety geometry across depth. Causal interventions show that early vision layers support strong bidirectional refusal control through activation steering along a learned safety direction, with unsafe rejection spanning 6%-96%, whereas later layers respond more to activation magnitude scaling and exhibit a substantial safety-selectivity trade-off. Deeper layers remain well separated along the safety direction yet are largely insensitive to steering, distinguishing representational separability from causal controllability. InternVL2.5-4B shows qualitatively similar depth-dependent activation geometry despite differences in layer location and magnitude. Our results expose a white-box, representation-level refusal-bypass attack surface in VLM vision encoders and motivate inference-time stabilization of safety-sensitive representations.