SoWaF: Shuffling of Weights and Feature Maps: A Novel Hardware Intrinsic Attack (HIA) on Convolutional Neural Network (CNN)

03/16/2021
by   Tolulope A. Odetola, et al.
0

Security of inference phase deployment of Convolutional neural network (CNN) into resource constrained embedded systems (e.g. low end FPGAs) is a growing research area. Using secure practices, third party FPGA designers can be provided with no knowledge of initial and final classification layers. In this work, we demonstrate that hardware intrinsic attack (HIA) in such a "secure" design is still possible. Proposed HIA is inserted inside mathematical operations of individual layers of CNN, which propagates erroneous operations in all the subsequent CNN layers that lead to misclassification. The attack is non-periodic and completely random, hence it becomes difficult to detect. Five different attack scenarios with respect to each CNN layer are designed and evaluated based on the overhead resources and the rate of triggering in comparison to the original implementation. Our results for two CNN architectures show that in all the attack scenarios, additional latency is negligible (<0.61 attack scenarios do not require any additional BRAM resources, while in two scenarios BRAM increases, which compensates with the corresponding decrease in FF and LUTs. To the authors' best knowledge this work is the first to address the hardware intrinsic CNN attack with the attacker does not have knowledge of the full CNN.

READ FULL TEXT

page 2

page 4

research
06/13/2021

FeSHI: Feature Map Based Stealthy Hardware Intrinsic Attack

Convolutional Neural Networks (CNN) have shown impressive performance in...
research
06/16/2020

How Secure is Distributed Convolutional Neural Network on IoT Edge Devices?

Convolutional Neural Networks (CNN) has found successful adoption in man...
research
06/17/2019

CheckNet: Secure Inference on Untrusted Devices

We introduce CheckNet, a method for secure inference with deep neural ne...
research
08/08/2017

Prune the Convolutional Neural Networks with Sparse Shrink

Nowadays, it is still difficult to adapt Convolutional Neural Network (C...
research
06/20/2022

Seizure Detection and Prediction by Parallel Memristive Convolutional Neural Networks

During the past two decades, epileptic seizure detection and prediction ...
research
04/02/2017

Understanding Deep Representations through Random Weights

We systematically study the deep representation of random weight CNN (co...
research
05/14/2018

Hu-Fu: Hardware and Software Collaborative Attack Framework against Neural Networks

Recently, Deep Learning (DL), especially Convolutional Neural Network (C...

Please sign up or login with your details

Forgot password? Click here to reset