FeSHI: Feature Map Based Stealthy Hardware Intrinsic Attack

06/13/2021
by   Tolulope Odetola, et al.
10

Convolutional Neural Networks (CNN) have shown impressive performance in computer vision, natural language processing, and many other applications, but they exhibit high computations and substantial memory requirements. To address these limitations, especially in resource-constrained devices, the use of cloud computing for CNNs is becoming more popular. This comes with privacy and latency concerns that have motivated the designers to develop embedded hardware accelerators for CNNs. However, designing a specialized accelerator increases the time-to-market and cost of production. Therefore, to reduce the time-to-market and access to state-of-the-art techniques, CNN hardware mapping and deployment on embedded accelerators are often outsourced to untrusted third parties, which is going to be more prevalent in futuristic artificial intelligence of things (AIoT) systems. These AIoT systems anticipate horizontal collaboration among different resource-constrained AIoT node devices, where CNN layers are partitioned and these devices collaboratively compute complex CNN tasks Therefore, there is a dire need to explore this attack surface for designing secure embedded hardware accelerators for CNNs. Towards this goal, in this paper, we exploited this attack surface to propose an HT-based attack called FeSHI. This attack exploits the statistical distribution i.e., Gaussian distribution, of the layer-by-layer feature maps of the CNN to design two triggers for stealthy HT with a very low probability of triggering. To illustrate the effectiveness of the proposed attack, we deployed the LeNet and LeNet-3D on PYNQ to classify the MNIST and CIFAR-10 datasets, respectively, and tested FeSHI. The experimental results show that FeSHI utilizes up to 2 LUTs, and the overall resource overhead is less than 1 original designs

READ FULL TEXT

page 1

page 3

page 8

page 10

page 11

page 12

page 14

page 15

research
03/16/2021

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

Security of inference phase deployment of Convolutional neural network (...
research
05/20/2016

Ristretto: Hardware-Oriented Approximation of Convolutional Neural Networks

Convolutional neural networks (CNN) have achieved major breakthroughs in...
research
05/02/2022

VSCNN: Convolution Neural Network Accelerator With Vector Sparsity

Hardware accelerator for convolution neural network (CNNs) enables real ...
research
02/15/2020

An Energy-Efficient Accelerator Architecture with Serial Accumulation Dataflow for Deep CNNs

Convolutional Neural Networks (CNNs) have shown outstanding accuracy for...
research
09/22/2021

Security Analysis of Capsule Network Inference using Horizontal Collaboration

The traditional convolution neural networks (CNN) have several drawbacks...
research
04/19/2020

HCM: Hardware-Aware Complexity Metric for Neural Network Architectures

Convolutional Neural Networks (CNNs) have become common in many fields i...

Please sign up or login with your details

Forgot password? Click here to reset