クリーン参照残差によるバックドア汚染サンプル検出
SCR: Detecting Backdoor-Poisoned Samples through Clean-Reference Residuals
少数のクリーン参照サンプルで各サンプルの特徴を再構成し、クリーン基準からの一貫した逸脱を検出することで、攻撃知識なしにバックドア汚染サンプルを高精度で特定する手法SCR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: Yi Yang, Jinyang Huang, Feng-Qi Cui, Yu-Tong Guo, Sirui Zhao, Haiming Jin, Weihua Li, Quan Bai, Meng Li
分類: cs.CV, cs.CR
原文アブストラクト
Deep neural networks are vulnerable to backdoor attacks, in which adversaries manipulate model predictions by injecting poisoned samples into training data. Detecting these samples remains challenging because legitimate semantic variation can obscure poisoning-related signals in learned representations. Consequently, class-level statistics used by existing detectors may flag benign feature deviations while overlooking poisoned samples that blend into the class distribution. In this paper, we propose Semantic Counterfactual Residualization (SCR), which uses a small set of clean reference samples to account for benign variation through sample-specific feature reconstruction. SCR identifies poisoned samples by detecting coherent deviations from these clean baselines, without requiring prior knowledge of the attacks. We evaluate SCR through experiments covering twelve dirty-label and clean-label attacks across CIFAR-10, CIFAR-100, and Tiny ImageNet. With a small clean-reference set, SCR achieves attack-averaged true positive rates above 99.5\% and false positive rates below 2\% on each dataset, outperforming eight representative detection baselines in macro-TPR.
