Hire-snn: Harnessing the inherent robustness of energy-efficient deep spiking neural networks by training with crafted input noise

S Kundu, M Pedram, PA Beerel - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Low-latency deep spiking neural networks (SNNs) have become a promising alternative to
conventional artificial neural networks (ANNs) because of their potential for increased …

Dvs-attacks: Adversarial attacks on dynamic vision sensors for spiking neural networks

A Marchisio, G Pira, M Martina… - … Joint Conference on …, 2021 - ieeexplore.ieee.org
Spiking Neural Networks (SNNs), despite being energy-efficient when implemented on
neuromorphic hardware and coupled with event-based Dynamic Vision Sensors (DVS), are …

[PDF][PDF] Toward robust spiking neural network against adversarial perturbation

L Liang, K Xu, X Hu, L Deng… - Advances in Neural …, 2022 - proceedings.neurips.cc
As spiking neural networks (SNNs) are deployed increasingly in real-world efficiency critical
applications, the security concerns in SNNs attract more attention. Currently, researchers …