Robustness Hidden in Plain Sight: Can Analog Computing Defend Against Adversarial Attacks?

08/27/2020
by   Deboleena Roy, et al.
0

The ever-increasing computational demand of Deep Learning has propelled research in special-purpose inference accelerators based on emerging non-volatile memory (NVM) technologies. Such NVM crossbars promise fast and energy-efficient in-situ matrix vector multiplications (MVM) thus alleviating the long-standing von Neuman bottleneck in today's digital hardware. However the analog nature of computing in these NVM crossbars introduces approximations in the MVM operations. In this paper, we study the impact of these non-idealities on the performance of DNNs under adversarial attacks. The non-ideal behavior interferes with the computation of the exact gradient of the model, which is required for adversarial image generation. In a non-adaptive attack, where the attacker is unaware of the analog hardware, we show that analog computing offers a varying degree of intrinsic robustness, with a peak adversarial accuracy improvement of 35.34 PGD (ϵ=1/255, iter=30) for CIFAR-10, CIFAR-100, and ImageNet(top-5) respectively. We also demonstrate "hardware-in-loop" adaptive attacks that circumvent this robustness by utilizing the knowledge of the NVM model. To the best of our knowledge, this is the first work that explores the non-idealities of analog computing for adversarial robustness at the time of submission to NeurIPS 2020.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/19/2021

On the Noise Stability and Robustness of Adversarially Trained Networks on NVM Crossbars

Applications based on Deep Neural Networks (DNNs) have grown exponential...
research
08/25/2020

Rethinking Non-idealities in Memristive Crossbars for Adversarial Robustness in Neural Networks

Deep Neural Networks (DNNs) have been shown to be prone to adversarial a...
research
02/15/2023

XploreNAS: Explore Adversarially Robust Hardware-efficient Neural Architectures for Non-ideal Xbars

Compute In-Memory platforms such as memristive crossbars are gaining foc...
research
06/22/2021

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

Adversarial input detection has emerged as a prominent technique to hard...
research
07/03/2018

Efficient ConvNets for Analog Arrays

Analog arrays are a promising upcoming hardware technology with the pote...
research
04/13/2021

Mitigating Adversarial Attack for Compute-in-Memory Accelerator Utilizing On-chip Finetune

Compute-in-memory (CIM) has been proposed to accelerate the convolution ...
research
05/09/2021

Efficiency-driven Hardware Optimization for Adversarially Robust Neural Networks

With a growing need to enable intelligence in embedded devices in the In...

Please sign up or login with your details

Forgot password? Click here to reset