Resilience of deep learning applications: A systematic literature review of analysis and hardening techniques

Abstract

Machine Learning (ML) is currently being exploited in numerous applications, being one of the most effective Artificial Intelligence (AI) technologies used in diverse fields, such as vision, autonomous systems, and the like. The trend motivated a significant amount of contributions to the analysis and design of ML applications against faults affecting the underlying hardware. The authors investigate the existing body of knowledge on Deep Learning (among ML techniques) resilience against hardware faults systematically through a thoughtful review in which the strengths and weaknesses of this literature stream are presented clearly and then future avenues of research are set out. The review reports 85 scientific articles published between January 2019 and March 2024, after carefully analysing 222 contributions (from an initial screening of eligible 244 publications). The authors adopt a classifying framework to interpret and highlight research similarities and peculiarities, based on several parameters, starting from the main scope of the work, the adopted fault and error models, to their reproducibility. This framework allows for a comparison of the different solutions and the identification of possible synergies. Furthermore, suggestions concerning the future direction of research are proposed in the form of open challenges to be addressed.