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

by   Alberto Marchisio, et al.
NYU college
Politecnico di Torino
TU Wien

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. Toward this, we propose DVS-Attacks, a set of stealthy yet efficient adversarial attack methodologies targeted to perturb the event sequences that compose the input of the SNNs. First, we show that noise filters for DVS can be used as defense mechanisms against adversarial attacks. Afterwards, we implement several attacks and test them in the presence of two types of noise filters for DVS cameras. The experimental results show that the filters can only partially defend the SNNs against our proposed DVS-Attacks. Using the best settings for the noise filters, our proposed Mask Filter-Aware Dash Attack reduces the accuracy by more than 20 and by more than 65 frames. The source code of all the proposed DVS-Attacks and noise filters is released at https://github.com/albertomarchisio/DVS-Attacks.


page 4

page 7

page 8

page 9


Adversarial Attacks on Spiking Convolutional Networks for Event-based Vision

Event-based sensing using dynamic vision sensors is gaining traction in ...

Security-Aware Approximate Spiking Neural Networks

Deep Neural Networks (DNNs) and Spiking Neural Networks (SNNs) are both ...

Explaining Away Attacks Against Neural Networks

We investigate the problem of identifying adversarial attacks on image-b...

DetectX – Adversarial Input Detection using Current Signatures in Memristive XBar Arrays

Adversarial input detection has emerged as a prominent technique to hard...

Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters

Deep Learning (DL) algorithms have gained popularity owing to their prac...

Please sign up or login with your details

Forgot password? Click here to reset