Analysis of Power-Oriented Fault Injection Attacks on Spiking Neural Networks

by   Karthikeyan Nagarajan, et al.

Spiking Neural Networks (SNN) are quickly gaining traction as a viable alternative to Deep Neural Networks (DNN). In comparison to DNNs, SNNs are more computationally powerful and provide superior energy efficiency. SNNs, while exciting at first appearance, contain security-sensitive assets (e.g., neuron threshold voltage) and vulnerabilities (e.g., sensitivity of classification accuracy to neuron threshold voltage change) that adversaries can exploit. We investigate global fault injection attacks by employing external power supplies and laser-induced local power glitches to corrupt crucial training parameters such as spike amplitude and neuron's membrane threshold potential on SNNs developed using common analog neurons. We also evaluate the impact of power-based attacks on individual SNN layers for 0 (i.e., whole layer under attack). We investigate the impact of the attacks on digit classification tasks and find that in the worst-case scenario, classification accuracy is reduced by 85.65 robust current driver design that is immune to power-oriented attacks, improved circuit sizing of neuron components to reduce/recover the adversarial accuracy degradation at the cost of negligible area and 25 present a dummy neuron-based voltage fault injection detection system with 1 power and area overhead.


page 1

page 2

page 3

page 4


Energy-Efficient High-Accuracy Spiking Neural Network Inference Using Time-Domain Neurons

Due to the limitations of realizing artificial neural networks on preval...

Ultra-Low Energy and High Speed LIF Neuron using Silicon Bipolar Impact Ionization MOSFET for Spiking Neural Networks

Silicon bipolar impact ionization MOSFET offers the potential for realiz...

Improving Spiking Neural Network Accuracy Using Time-based Neurons

Due to the fundamental limit to reducing power consumption of running de...

NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips

Due to their proven efficiency, machine-learning systems are deployed in...

Improving Reliability of Spiking Neural Networks through Fault Aware Threshold Voltage Optimization

Spiking neural networks have made breakthroughs in computer vision by le...

Spiking-YOLO: Spiking Neural Network for Real-time Object Detection

Over the past decade, deep neural networks (DNNs) have become a de-facto...

Advancing Residual Learning towards Powerful Deep Spiking Neural Networks

Despite the rapid progress of neuromorphic computing, inadequate capacit...

Please sign up or login with your details

Forgot password? Click here to reset