no code implementations • 18 Jan 2023 • Yusuke Kawamoto, Kazumasa Miyake, Koichi Konishi, Yutaka Oiwa
In this article, we propose the Artificial Intelligence Security Taxonomy to systematize the knowledge of threats, vulnerabilities, and security controls of machine-learning-based (ML-based) systems.
1 code implementation • 7 Jan 2021 • Tinghui Ouyang, Vicent Sant Marco, Yoshinao Isobe, Hideki Asoh, Yutaka Oiwa, Yoshiki Seo
However, the complex architecture and the huge amount of parameters make the robust adjustment of DL models not easy, meanwhile it is not possible to generate all real-world corner cases for DL training.