Paper 2019/461

Physical Security of Deep Learning on Edge Devices: Comprehensive Evaluation of Fault Injection Attack Vectors

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

Abstract

Decision making tasks carried out by the usage of deep neural networks are successfully taking over in many areas, including those that are security critical, such as healthcare, transportation, smart grids, where intentional and unintentional failures can be disastrous. Edge computing systems are becoming ubiquitous nowadays, often serving deep learning tasks that do not need to be sent over to servers. Therefore, there is a necessity to evaluate the potential attacks that can target deep learning in the edge. In this work, we present evaluation of deep neural networks (DNNs) reliability against fault injection attacks. We first experimentally evaluate DNNs implemented in an embedded device by using laser fault injection to get the insight on possible attack vectors. We show practical results on four activation functions, ReLu, softmax, sigmoid, and tanh. We then perform a deep study on DNNs based on derived fault models by using several different attack strategies based on random faults. We also investigate a powerful attacker who can find effective fault location based on genetic algorithm, to show the most efficient attacks in terms of misclassification success rates. Finally, we show how a state of the art countermeasure against model extraction attack can be bypassed with a fault attack. Our results can serve as a basis to outline the susceptibility of DNNs to physical attacks which can be considered a viable attack vector whenever a device is deployed in hostile environment.

Metadata
Available format(s)
PDF
Category
Implementation
Publication info
Published elsewhere. Minor revision.Microelectronics Reliability
DOI
10.1016/j.microrel.2021.114116
Keywords
fault attackneural networkdeep learning
Contact author(s)
jakub breier @ gmail com
History
2021-04-19: last of 2 revisions
2019-05-10: received
See all versions
Short URL
https://ia.cr/2019/461
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2019/461,
      author = {Xiaolu Hou and Jakub Breier and Dirmanto Jap and Lei Ma and Shivam Bhasin and Yang Liu},
      title = {Physical Security of Deep Learning on Edge Devices: Comprehensive Evaluation of Fault Injection Attack Vectors},
      howpublished = {Cryptology ePrint Archive, Paper 2019/461},
      year = {2019},
      doi = {10.1016/j.microrel.2021.114116},
      note = {\url{https://eprint.iacr.org/2019/461}},
      url = {https://eprint.iacr.org/2019/461}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.