Spikewhisper: Temporal Spike Backdoor Attacks on Federated Neuromorphic Learning over Low-power Devices

arXiv:2403.18607v1 Announce Type: new
Abstract: Federated neuromorphic learning (FedNL) leverages event-driven spiking neural networks and federated learning frameworks to effectively execute intelligent analysis tasks over amounts of distributed low-power devices but also perform vulnerability to poisoning attacks. The threat of backdoor attacks on traditional deep neural networks typically comes from time-invariant data. However, in FedNL, unknown threats may be hidden in time-varying spike signals. In this paper, we start to explore a novel vulnerability of FedNL-based systems with the concept …

analysis arxiv attacks backdoor backdoor attacks cs.ai cs.cr devices distributed eess.sp effectively event federated federated learning frameworks low networks neural networks poisoning poisoning attacks power temporal threat vulnerability