Visible to the public Biblio

Filters: Author is Shibagaki, Kazuya  [Clear All Filters]
2021-11-29
Takemoto, Shu, Shibagaki, Kazuya, Nozaki, Yusuke, Yoshikawa, Masaya.  2020.  Deep Learning Based Attack for AI Oriented Authentication Module. 2020 35th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC). :5–8.
Neural Network Physical Unclonable Function (NN-PUF) has been proposed for the secure implementation of Edge AI. This study evaluates the tamper resistance of NN-PUF against machine learning attacks. The machine learning attack in this study learns CPRs using deep learning. As a result of the evaluation experiment, the machine learning attack predicted about 82% for CRPs. Therefore, this study revealed that NN-PUF is vulnerable to machine learning attacks.