T-Backdoor: Exploiting Temporal Redundancy in Neuromorphic Data for Spike-preserving Backdoor Attacks on SNNs
T-Backdoor uses purely temporal triggers to backdoor spiking neural networks, reaching about 100% success against seven defenses.
T-Backdoor is a backdoor attack on spiking neural networks that uses only temporal triggers—Rate, Latency, and Jitter—without spatial changes to the input. On N-MNIST, CIFAR10-DVS, and N-Caltech101, the authors report about 100% attack success in single- and multi-target settings with only minor clean-accuracy loss. The attack remained effective against seven existing backdoor detection and mitigation methods. Code is published in the SiSL-URI GitHub repository.
- Uses only temporal triggers: Rate, Latency, and Jitter, with no spatial change.
- Reports about 100% attack success on N-MNIST, CIFAR10-DVS, and N-Caltech101.
- Stayed effective against seven backdoor defenses with minor clean-accuracy loss.
Full article148 words · extracted from arxiv.org · click to collapse
Backdoor attacks are a serious security threat to deep neural networks (DNNs) and remain largely underexplored for spiking neural networks (SNNs). Existing attacks primarily introduce spatiotemporal triggers that induce deviations in the spike distribution of poisoned samples relative to their clean counterparts. To address this limitation, this work proposes a novel backdoor attack on SNNs, termed \textbf{T-Backdoor}, which operates using purely temporal triggers such as \textit{Rate}, \textit{Latency}, and \textit{Jitter} without introducing any spatial perturbation, making the shift in spike distributions significantly harder to detect. Through extensive experiments on three benchmark neuromorphic datasets: N-MNIST, CIFAR10-DVS, and N-Caltech101, and evaluation against seven baseline backdoor defense methods, we demonstrate that T-Backdoor achieves a near-perfect 100\% attack success rate (ASR) in both single target and multi target settings with only minor degradation in clean accuracy, while remaining robust against existing backdoor detection and mitigation techniques. The codes are available at https://github.com/SiSL-URI/T-Backdoor .
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.30119