| Title | Resiliency of SNN on Black-Box Adversarial Attacks |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Paudel, Bijay Raj, Itani, Aashish, Tragoudas, Spyros |
| Conference Name | 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) |
| Keywords | adversarial attacks, black-box attacks, Conferences, Deep Neural Network, Hardware, machine learning, neural network resiliency, Neural networks, Neuromorphics, pubcrawl, resilience, Resiliency, Robustness, Software, spiking neural network, SpiNNaker |
| Abstract | Existing works indicate that Spiking Neural Networks (SNNs) are resilient to adversarial attacks by testing against few attack models. This paper studies adversarial attacks on SNNs using additional attack models and shows that SNNs are not inherently robust against many few-pixel L0 black-box attacks. Additionally, a method to defend against such attacks in SNNs is presented. The SNNs and the effects of adversarial attacks are tested on both software simulators as well as on SpiNNaker neuromorphic hardware. |
| DOI | 10.1109/ICMLA52953.2021.00132 |
| Citation Key | paudel_resiliency_2021 |
Resiliency of SNN on Black-Box Adversarial Attacks