A new approach for machine learning security risk assessment: work in progress

Jun Yajima, Maki Inui, Takanori Oikawa, Fumiyoshi Kasahara, Ikuya Morikawa, Nobukazu Yoshioka

Abstract: We propose a new security risk assessment approach for Machine Learning-based AI systems (ML systems). The assessment of security risks of ML systems requires expertise in ML security. So, ML system developers, who may not know much about ML security, cannot assess the security risks of their systems. By using our approach, a ML system developers can easily assess the security risks of the ML system. In performing the assessment, the ML system developer only has to answer the yes/no questions about the specification of the ML system. In our trial, we confirmed that our approach works correctly.