Artificial Intelligence (AI) - Machine Learning (ML) algorithms specifically - are increasingly being used in different aspects of our life like autonomous vehicles, power plants, medical robots, and other systems. Some of these applications require meeting a specific safety standard for all the involving components, which includes the AI part.

However, due to unpredictable nature of ML algorithms, there are no standards applicable to the topic at the moment, which rises an interesting research topic to work on. This project aims to find a way around the problem by taking currently existing protocols and filling in the gap between the standards and the algorithms.