A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networks

Sharmin, Saima; Panda, Priyadarshini; Sarwar, Syed Shakib; Lee, Chankyu; Ponghiran, Wachirawit; Roy, Kaushik

doi:10.1109/ijcnn.2019.8851732

Cited by 50 publications

(18 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are various alternatives to Rueckauer's method [34] to optimize the transfer from ReLU NN to spiking NNs. For example, [46] provides impressive results in the context of adversarial AI. In our present study, we explored several ways to search for optimal scaling parameters, including particle swarm optimization (PSO) [47], and simple exhaustive grid search.…”

Section: Conversion Of Trained Relu Nn To Snnmentioning

confidence: 99%

Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to Atari Breakout game

et al. 2019

View full text Add to dashboard Cite

Section: Conversion Of Trained Relu Nn To Snnmentioning

confidence: 99%

Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to Atari Breakout game

et al. 2019

View full text Add to dashboard Cite

“…Previous studies [43,42] have shown that SNNs are more robust to adversarial inputs than ANNs. In order to observe the effectiveness of SNNs under attack, we conduct a qualitative and quantitative comparison between Grad-CAM and SAM.…”

Section: Adversarial Robustness Of Snnmentioning

confidence: 99%

Visual Explanations from Spiking Neural Networks using Interspike Intervals

Kim,

Panda

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Spiking Neural Networks (SNNs) compute and communicate with asynchronous binary temporal events that can lead to significant energy savings with neuromorphic hardware. Recent algorithmic efforts on training SNNs have shown competitive performance on a variety of classification tasks. However, a visualization tool for analysing and explaining the internal spike behavior of such temporal deep SNNs has not been explored. In this paper, we propose a new concept of bio-plausible visualization for SNNs, called Spike Activation Map (SAM). The proposed SAM circumvents the non-differentiable characteristic of spiking neurons by eliminating the need for calculating gradients to obtain visual explanations. Instead, SAM calculates a temporal visualization map by forward propagating input spikes over different time-steps. SAM yields an attention map corresponding to each time-step of input data by highlighting neurons with short inter-spike interval activity. Interestingly, without both the backpropagation process and the class label, SAM highlights the discriminative region of the image while capturing fine-grained details. With SAM, for the first time, we provide a comprehensive analysis on how internal spikes work in various SNN training configurations depending on optimization types, leak behavior, as well as when faced with adversarial examples.

show abstract

“…Recently, adversarial attacks for SNNs have been explored, working in black-box [14] and white-box settings [13]. Sharmin et al [15] proposed a methodology to attack (non-spiking) DNNs, and then the adversarial examples mislead the equivalent converted SNNs. Liang et al [16] proposed a gradient-based adversarial attack methodology for SNNs.…”

Section: Adversarial Attacks and Security Threats For Snns In The Spa...mentioning

confidence: 99%

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

Marchisio¹,

Pira²,

Martina³

et al. 2021

Preprint

View full text Add to dashboard Cite

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% on the DVS-Gesture dataset and by more than 65% on the MNIST dataset, compared to the original clean frames. The source code of all the proposed DVS-Attacks and noise filters is released at https://github.com/albertomarchisio/DVS-Attacks.

show abstract

A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networks

Cited by 50 publications

References 10 publications

Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to Atari Breakout game

Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to Atari Breakout game

Visual Explanations from Spiking Neural Networks using Interspike Intervals

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

Contact Info

Product

Resources

About