Vis-Poison: マルチモーダル検索拡張生成における視覚知識の毒化攻撃
Vis-Poison: Poisoning Visual Knowledge in Multimodal Retrieval-Augmented Generation
画像自体を攻撃ペイロードとして用い、キャプション等のテキストを改変せずにマルチモーダルRAGシステムを欺く新たな毒化攻撃を提案し、ブラックボックス環境で高い成功率を実証した。
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: Rujin Liang, Zhongpu Chen, Yuhao Lei, Xin Miao
分類: cs.CV, cs.AI
原文アブストラクト
While multimodal retrieval-augmented generation (RAG) systems increasingly rely on images as external knowledge sources, the introduction of poisoned visual evidence can severely compromise multimodal large language model (MLLM) generation. Unlike prior attacks that rely on altering textual metadata, we introduce Vis-Poison, a novel visual knowledge poisoning attack where the poisoned image itself is the attacker-controlled payload, without manipulating captions, summaries, metadata, or other associated text. Specifically, this attack is instantiated through an automated multi-agent method that constructs visually plausible poisoned images. To assess its impact, we evaluate Vis-Poison across two representative multimodal RAG pipelines, four embedding models, and six generation models. Empirically, Vis-Poison achieves an end-to-end attack success rate of 40.16\% to 65.40\% against 30k-entry multimodal knowledge bases in \emph{black-box} settings. Moreover, Vis-Poison remains effective against various MLLMs that can answer correctly from parametric knowledge alone, with an average success rate above 60\%. Code and data are available at https://github.com/SWUFE-DB-Group/Vis-Poison.