A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
It addresses safety and trustworthiness concerns for DNNs in applications like self-driving cars, but is incremental as a survey.
This survey paper reviews research on making deep neural networks safe and trustworthy, covering verification, testing, adversarial attack and defence, and interpretability, based on 202 papers mostly published after 2017.
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.