A New SVDD Approach to Reliable and Explainable AI

Safety engineering and artificial intelligence are two fields that still need investigation on their reciprocal interactions. Safety should be guaranteed when autonomous decision may lead to risk for the environment and the human. The present work addresses how support vector data description (SVDD) can be redesigned to detect safety regions in a cyber-physical system with zero statistical error. Rule-based knowledge extraction is also presented, to let the SVDD be understandable. Two applications are considered for performance evaluation, (i) domain name server tunneling detection and (ii) region of attraction estimation of dynamic systems. Results demonstrate how the new SVDD and its intelligible representation are both suitable in designing safety regions, still maximizing the space of the working conditions.

In IEEE Intelligent Systems