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


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 Journal/MagazineJournal articlepeer-review

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


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.