Home > Research > Publications & Outputs > A survey of safety and trustworthiness of deep ...

Links

Text available via DOI:

View graph of relations

A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability

Research output: Contribution to journalJournal articlepeer-review

Published
  • X. Huang
  • D. Kroening
  • W. Ruan
  • J. Sharp
  • Y. Sun
  • E. Thamo
  • M. Wu
  • X. Yi
Close
Article number100270
<mark>Journal publication date</mark>1/08/2020
<mark>Journal</mark>Computer Science Review
Volume37
Number of pages35
Publication StatusPublished
Early online date17/06/20
<mark>Original language</mark>English

Abstract

In the past few years, significant progress has been made on deep neural networks (DNNs) in achieving human-level performance on several long-standing tasks. With the broader deployment of DNNs on various applications, the concerns over their safety and trustworthiness have been raised in public, especially after the widely reported fatal incidents involving self-driving cars. Research to address these concerns is particularly active, with a significant number of papers released in the past few years. This survey paper conducts a review of the current research effort into making DNNs safe and trustworthy, by focusing on four aspects: verification, testing, adversarial attack and defence, and interpretability. In total, we survey 202 papers, most of which were published after 2017.