Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challenges

TL;DR

This paper surveys the resilience and security of deep neural networks against both intentional and unintentional perturbations, highlighting research challenges and fostering cross-domain understanding for deploying robust DNNs in critical applications.

Contribution

It provides the first unified survey connecting the resilience of DNNs to both types of perturbations and discusses key research challenges for secure and robust deployment.

Findings

Identifies similarities between approaches for handling different perturbations

Highlights the need for unified research frameworks

Outlines challenges for deploying resilient DNNs in high-stakes scenarios

Abstract

In order to deploy deep neural networks (DNNs) in high-stakes scenarios, it is imperative that DNNs provide inference robust to external perturbations - both intentional and unintentional. Although the resilience of DNNs to intentional and unintentional perturbations has been widely investigated, a unified vision of these inherently intertwined problem domains is still missing. In this work, we fill this gap by providing a survey of the state of the art and highlighting the similarities of the proposed approaches.We also analyze the research challenges that need to be addressed to deploy resilient and secure DNNs. As there has not been any such survey connecting the resilience of DNNs to intentional and unintentional perturbations, we believe this work can help advance the frontier in both domains by enabling the exchange of ideas between the two communities.