English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

As spiking neural networks (SNNs) are deployed increasingly in real-worldefficiency critical applications, the security concerns in SNNs attract moreattention. Currently, researchers have already demonstrated an SNN can beattacked with adversarial examples. How to build a robust SNN becomes an urgentissue. Recently, many studies apply certified training in artificial neuralnetworks (ANNs), which can improve the robustness of an NN model promisely.However, existing certifications cannot transfer to SNNs directly because ofthe distinct neuron behavior and input formats for SNNs. In this work, we firstdesign S-IBP and S-CROWN that tackle the non-linear functions in SNNs' neuronmodeling. Then, we formalize the boundaries for both digital and spike inputs.Finally, we demonstrate the efficiency of our proposed robust training methodin different datasets and model architectures. Based on our experiment, we canachieve a maximum $37.7\%$ attack error reduction with $3.7\%$ originalaccuracy loss. To the best of our knowledge, this is the first analysis onrobust training of SNNs.

Toward Robust Spiking Neural Network Against Adversarial Perturbation