Sophia Antipolis, 19 January 2021
The ETSI Securing Artificial Intelligence Industry Specification Group (SAI ISG) last month released its first Group Report, ETSI GR SAI 004, which gives an overview of the problem statement regarding the securing of AI. ETSI SAI is the first standardization initiative dedicated to securing AI.
The Report describes the problem of securing AI-based systems and solutions, with a focus on machine learning, and the challenges relating to confidentiality, integrity and availability at each stage of the machine learning lifecycle. It also points out some of the broader challenges of AI systems including bias, ethics and ability to be explained. A number of different attack vectors are outlined, as well as several cases of real-world use and attacks.