Seminar: Multi-Dimensional Certification of Artificial Intelligence
On May 30, 023, I am going to hold a seminar entitled Multi-Dimensional Certification of Artificial Intelligence, within the event Building Bridges through Multidisciplinary Cooperation: Perspective Approaches for Inclusive Artificial Intelligence at Università degli Studi di Milano.
The abstract of the seminar is:
Machine Learning (ML) is increasingly used to drive the operation of complex distributed systems deployed on the cloud-edge continuum enabled by 5G. Correspondingly, distributed systems’ behavior is becoming more non-deterministic in nature. This evolution of distributed systems requires the definition of new assurance approaches for the verification of non-functional properties. Certification, the most popular assurance technique for system and software verification, is not immediately applicable to systems whose behavior is determined by Machine Learning-based inference. However, there is an increasing push from policy makers, regulators, and industrial stakeholders towards the definition of techniques for the certification of non-functional properties (e.g., fairness, robustness, privacy) of ML. This article analyzes the challenges and deficiencies of current certification schemes, discusses open research issues and proposes a first certification scheme for ML-based distributed systems.