Using Undervolting as an on-Device Defense Against Adversarial Machine Learning Attacks
Authors:
- 12 December 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 158-169
Abstract
Deep neural network (DNN) classifiers are powerful tools that drive a broad spectrum of important applications, from image recognition to autonomous vehicles. Unfortunately, DNNs are known to be vulnerable to adversarial attacks that affect virtually all state-of-the-art models. These attacks make small imperceptible modifications to inputs that are sufficient to induce the DNNs to produce the wrong classification. In this paper we propose a novel, lightweight adversarial correction and/or detection mechanism for image classifiers that relies on undervolting (running a chip at a voltage that is slightly below its safe margin). We propose using controlled undervolting of the chip running the inference process in order to introduce a limited number of compute errors. We show that these errors disrupt the adversarial input in a way that can be used either to correct the classification or detect the input as adversarial. We evaluate the proposed solution in an FPGA design and through software simulation. We evaluate 10 attacks and show average detection rates of 77% and 90% on two popular DNNs.Keywords
All Related Versions
Funding Information
- National Science Foundation (CCF-2028944,CCF-1629392)
- Air Force Research Laboratory (FA8650-20-C-1719)
This publication has 29 references indexed in Scilit:
- Towards Evaluating the Robustness of Neural Networks2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks2016
- The Limitations of Deep Learning in Adversarial Settings2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- GPU voltage noise: Characterization and hierarchical smoothing of spatial and temporal voltage noise interference in GPU architectures2015
- Dynamic reduction of voltage margins by leveraging on-chip ECC in Itanium II processors2013
- Active management of timing guardband to save energy in POWER72011
- Razor: a low-power pipeline based on circuit-level timing speculation2003