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.
From the original article
1 min read at arxiv.orgBackdoor 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.
By Abdullah Arafat Miah · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.