LATIDIA · Ciberseguridad
SCR: Detección de muestras contaminadas por «backdoors» mediante residuos de referencia limpios
arXiv:2611.24558v1 Tipo de anuncio: cruzado Resumen: Las redes neuronales profundas son vulnerables a los ataques de «puerta trasera», en los que los adversarios manipulan las predicciones del modelo inyectando muestras contaminadas en los datos de entrenamiento. Detectar los
WhatsApp ↗Telegram ↗
La noticia
arXiv:2611.24558v1 Announce Type: cross Abstract: 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.