LATIDIA · Ciberseguridad

Ataque de inferencia de membresía de Power Side-Channel en el aprendizaje automático integrado

arXiv:2610.10909v1 Tipo de anuncio: nuevo Resumen: Los ataques de inferencia de membresía (mias) amenazan la privacidad de los datos de entrenamiento de aprendizaje automático (ML) al determinar si se utilizó una muestra para entrenar un modelo de destino. M existente

La noticia

arXiv:2610.10909v1 Announce Type: new Abstract: Membership inference attacks (MIAs) threaten the privacy of machine learning (ML) training data by determining whether a sample was used to train a target model. Existing MIAs rely on model outputs, ranging from prediction probabilities to predicted labels, an assumption that can be restrictive for on-device ML systems with limited or inaccessible outputs. However, suppressing model outputs does not eliminate the data-dependent computations that produce them, which may remain observable through physical side channels. We present PSCMIA, a power side-channel membership inference attack against embedded ML models that can infer membership directly from power traces without requiring prediction probabilities or even the predicted labels. We