R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensors

1 code implementation • 1 Sep 2021 • Alberto Marchisio, Giacomo Pira, Maurizio Martina, Guido Masera, Muhammad Shafique

Spiking Neural Networks (SNNs) aim at providing energy-efficient learning capabilities when implemented on neuromorphic chips with event-based Dynamic Vision Sensors (DVS).

DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural Networks

1 code implementation • 1 Jul 2021 • Alberto Marchisio, Giacomo Pira, Maurizio Martina, Guido Masera, Muhammad Shafique

Spiking Neural Networks (SNNs), despite being energy-efficient when implemented on neuromorphic hardware and coupled with event-based Dynamic Vision Sensors (DVS), are vulnerable to security threats, such as adversarial attacks, i. e., small perturbations added to the input for inducing a misclassification.

Adversarial Attack