クラウドエッジ推論における大規模視覚言語モデルへの視覚トークン操作攻撃
Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models
エッジとクラウド間で送信される視覚トークンを攻撃者が改ざんし、モデルの精度を大幅に低下させる攻撃手法を提案・評価した論文。
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: Zikai Zhang, Rui Hu, Olivera Kotevska, Jiahao Xu
分類: cs.CR, cs.AI, cs.CV
原文アブストラクト
Cloud-edge Large Vision-Language Model (LVLM) inference enables efficient deployment by splitting computation between edge devices and cloud servers. In this process, intermediate vision tokens are transmitted from the edge to the cloud over a communication link, thereby exposing a new attack surface. We study vision token manipulation attack (VTM-Attack) under a black-box man-in-the-middle setting, where an adversary intercepts and manipulates a subset of transmitted vision tokens under a budget constraint. We propose four naïve attack strategies and an optimization-based token selection method. Experiments on 6 state-of-the-art LVLMs (3B-72B) across 4 benchmarks show that manipulating only 10\% of vision tokens can reduce accuracy by up to 88.31\%. These results reveal a critical vulnerability in cloud-edge LVLM inference.
