Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient

by   Ling Liang, et al.

Recently, backpropagation through time inspired learning algorithms are widely introduced into SNNs to improve the performance, which brings the possibility to attack the models accurately given Spatio-temporal gradient maps. We propose two approaches to address the challenges of gradient input incompatibility and gradient vanishing. Specifically, we design a gradient to spike converter to convert continuous gradients to ternary ones compatible with spike inputs. Then, we design a gradient trigger to construct ternary gradients that can randomly flip the spike inputs with a controllable turnover rate, when meeting all zero gradients. Putting these methods together, we build an adversarial attack methodology for SNNs trained by supervised algorithms. Moreover, we analyze the influence of the training loss function and the firing threshold of the penultimate layer, which indicates a "trap" region under the cross-entropy loss that can be escaped by threshold tuning. Extensive experiments are conducted to validate the effectiveness of our solution. Besides the quantitative analysis of the influence factors, we evidence that SNNs are more robust against adversarial attack than ANNs. This work can help reveal what happens in SNN attack and might stimulate more research on the security of SNN models and neuromorphic devices.


page 1

page 10

page 13

page 14


EventProp: Backpropagation for Exact Gradients in Spiking Neural Networks

We derive the backpropagation algorithm for spiking neural networks comp...

Gradient Scaling on Deep Spiking Neural Networks with Spike-Dependent Local Information

Deep spiking neural networks (SNNs) are promising neural networks for th...

A Temporally and Spatially Local Spike-based Backpropagation Algorithm to Enable Training in Hardware

Spiking Neural Networks (SNNs) have emerged as a hardware efficient arch...

Synthesizing Images from Spatio-Temporal Representations using Spike-based Backpropagation

Spiking neural networks (SNNs) offer a promising alternative to current ...

Exact Gradient Computation for Spiking Neural Networks Through Forward Propagation

Spiking neural networks (SNN) have recently emerged as alternatives to t...

Loss shaping enhances exact gradient learning with EventProp in Spiking Neural Networks

In a recent paper Wunderlich and Pehle introduced the EventProp algorith...

Dynamics-aware Adversarial Attack of Adaptive Neural Networks

In this paper, we investigate the dynamics-aware adversarial attack prob...

Please sign up or login with your details

Forgot password? Click here to reset