MLSMM: Machine Learning Security Maturity Model

Felix Viktor Jedrzejewski, Davide Fucci, Oleksandr Adamov

Keywords: AML, Maturity Model

Abstract:

Assessing the maturity of security practices during the development of Machine Learning (ML) based software components has not gotten as much attention as traditional software development.
In this Blue Sky idea paper, we propose an initial Machine Learning Security Maturity Model (MLSMM) which organizes security practices along the ML-development lifecycle and, for each, establishes three levels of maturity.
We envision MLSMM as a step towards closer collaboration between industry and academia.

Submission Number: 26