Security Evaluation of Deep Neural Network Resistance against Laser Fault Injection

Xiaolu Hou, Jakub Breier, Dirmanto Jap, Lei Ma, Shivam Bhasin, Yang Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep learning is becoming a basis of decision making systems in many application domains, such as autonomous vehicles, health systems, etc., where the risk of misclassification can lead to serious consequences. It is necessary to know to which extent are Deep Neural Networks (DNNs) robust against various types of adversarial conditions. In this paper, we experimentally evaluate DNNs implemented in embedded device by using laser fault injection, a physical attack technique that is mostly used in security and reliability communities to test robustness of various systems. We show practical results on four activation functions, ReLu, softmax, sigmoid, and tanh. Our results point out the misclassification possibilities for DNNs achieved by injecting faults into the hidden layers of the network. We evaluate DNNs by using several different attack strategies to show which are the most efficient in terms of misclassification success rates. Outcomes of this work should be taken into account when deploying devices running DNNs in environments where malicious attacker could tamper with the environmental parameters that would bring the device into unstable conditions. resulting into faults.

Original languageEnglish
Title of host publication2020 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits, IPFA 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728161693
DOIs
Publication statusPublished - Jul 20 2020
Event2020 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits, IPFA 2020 - Singapore, Singapore
Duration: Jul 20 2020Jul 23 2020

Publication series

NameProceedings of the International Symposium on the Physical and Failure Analysis of Integrated Circuits, IPFA
Volume2020-July

Conference

Conference2020 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits, IPFA 2020
CountrySingapore
CitySingapore
Period7/20/207/23/20

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Security Evaluation of Deep Neural Network Resistance against Laser Fault Injection'. Together they form a unique fingerprint.

Cite this