Guidance
Machine learning principles
These principles help developers, engineers, decision makers and risk owners make informed decisions about the design, development, deployment and operation of their machine learning (ML) systems.
Page 2 of 22
Part 1: Secure design
iStock.com/dem10
This section contains principles that apply to the design stage of the ML system development life cycle.
It covers understanding risks and threat modelling, as well as specific topics and trade-offs to consider. Crucially, it also highlights the need to ensure that your staff are aware of the importance of ‘secure by design’, both across ML components and the wider system.