← 研踪 PaperTrailarXiv:2611.24558 · v1
SCR: Detecting Backdoor-Poisoned Samples through Clean-Reference Residuals
首次提交 2026-11-18 22:57
版本更新 2026-11-18 22:57
雷达观测 2026-11-19 15:04
摘要
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.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-18 22:57 · 最新观测版本
SCR: Detecting Backdoor-Poisoned Samples through Clean-Reference Residuals
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.
查看此版本解读 →查看此版本原文 ↗