SemPurify: 意味情報を考慮したブラックボックスバックドア防御のためのデータ浄化
SemPurify: Semantics-Aware Data Purification for Black-box Backdoor Defense
画像変換でバックドアを破壊しつつ、低次・高次の意味情報をT2Iモデルで復元に用いることで、視覚・意味情報を保ちながらバックドアを除去するブラックボックス防御手法を提案した。
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: Jiawei Yu, Syed Irfan Ali Meerza, Yi Wu, Amir Sadovnik, Jian Liu
分類: cs.CV
原文アブストラクト
Backdoor attacks have emerged as a critical security threat in machine learning, where adversaries embed triggers within poisoned training samples to manipulate a model's predictions on targeted inputs while leaving its general behavior unaffected. This stealthy nature makes backdoor attacks difficult to detect, as the model functions normally until activated by a specific malicious trigger. Current purification-based defenses use image transformations (e.g., blurring) to disrupt trigger patterns but often degrade image quality. Even with advanced restoration techniques like diffusion models, these approaches can still alter visual or semantic information, reducing utility for downstream tasks. To address this, we propose the first semantics-aware data purification framework for black-box backdoor defense, SemPurify, which explicitly incorporates multi-level semantics (i.e., low-level semantic embeddings and high-level image tags) within a text-to-image (T2I) framework to guide image restoration during purification. Using this semantic information, the T2I model subsequently refines the transformed samples, helping preserve visual details and semantic information during restoration. Extensive experiments spanning multiple backdoor scenarios, i.e., classification models, CLIP-style encoders, and generative models, demonstrate that SemPurify reliably removes backdoors while effectively preserving semantic information for downstream tasks.