Moving Target Defense Through Approximation for Low-Power Neuromorphic Edge Intelligence

Neuromorphic intelligence is driven by spiking neural networks (SNNs) to achieve high algorithmic performance. However, similar to artificial neural networks (ANNs), SNNs are vulnerable to adversarial attacks. Such attacks often succeed in misclassification by repeatedly probing a fixed target model. Recent works claim that repeated attacks can be defended in ANNs by employing a moving target defense (MTD). Nonetheless, the state-of-the-art defense mechanisms in SNNs do not consider the notion of moving targets and are limited to shallow network architectures. To this end, we propose a novel MTD strategy for neuromorphic edge intelligence (MTSpike) that incorporates approximate knowledge distillation based on the distinct inherent structural parameters, i.e., firing threshold and time steps in SNNs, under a pretrain and finetune paradigm. Indeed, it is a 2-in-1 approach that enhances robustness against repeated attacks and reduces energy consumption for deeper SNNs. We evaluate our proposed MTSpike with four benchmark image classification datasets, i.e., ImageNet, CIFAR10, DVS128 Gesture, and CIFAR10-dynamic vision sensor datasets against white-box, black-box, and gray-box fast gradient sign method, projected gradient descent, sparse and efficiency attacks on deep residual SNNs. Our results demonstrate that MTSpike outperforms the state-of-the-art defense techniques by enabling SNNs to operate with a negligible drop in classification accuracy (as low as 1%–2%) under adversarial attacks. Also, MTSpike achieves
$1.3\times $
higher energy efficiency under efficiency attack. Apart from defense, MTSpike provides an additional advantage of energy efficiency by reducing the spike rate by
$3\times $
in deeper SNNs.