Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs

본문 미리보기

arXiv:2607.28075v1 Announce Type: new Abstract: Backdoor attacks on Spiking Neural Networks (SNNs) have primarily assumed dirty-label poisoning, in which triggered training samples are relabeled to an attacker-selected class. We study clean-label temporal poisoning, where a fixed timestamp transformation is applied only to the target-class training streams, leaving their labels unchanged. The transformation preserves the per-pixel, per-polarity event count exactly, making clean and triggered sa