SCANN: Side Channel Analysis of Spiking Neural Networks

Cryptography

article

Karthikeyan Nagarajan¹  Rupshali Roy¹  Rasit Onur Topaloglu²  Sachhidh Kannan³  Swaroop Ghosh¹ 

[1]School of Electrical Engineering and Computer Science, The Pennsylvania State University, State College

[2]IBM Corporation

[3]Ampere Computing

关键词: spiking neural networks;    side channel analysis;    reverse engineering;   

DOI  :  10.3390/cryptography7020017

学科分类：社会科学、人文和艺术（综合）

来源: mdpi

【 摘 要 】

Spiking neural networks (SNNs) are quickly gaining traction as a viable alternative to deep neural networks (DNNs). Compared to DNNs, SNNs are computationally more powerful and energy efficient. The design metrics (synaptic weights, membrane threshold, etc.) chosen for such SNN architectures are often proprietary and constitute confidential intellectual property (IP). Our study indicates that SNN architectures implemented using conventional analog neurons are susceptible to side channel attack (SCA). Unlike the conventional SCAs that are aimed to leak private keys from cryptographic implementations, SCANN (SCA ̲of spiking n ̲eural n ̲etworks) can reveal the sensitive IP implemented within the SNN through the power side channel. We demonstrate eight unique SCANN attacks by taking a common analog neuron (axon hillock neuron) as the test case. We chose this particular model since it is biologically plausible and is hence a good fit for SNNs. Simulation results indicate that different synaptic weights, neurons/layer, neuron membrane thresholds, and neuron capacitor sizes (which are the building blocks of SNN) yield distinct power and spike timing signatures, making them vulnerable to SCA. We show that an adversary can use templates (using foundry-calibrated simulations or fabricating known design parameters in test chips) and analysis to identify the specifications of the implemented SNN.

【 授权许可】

CC BY