Deep Learning based Attack for AI oriented Authentication Module
Shu Takemoto, Kazuya Shibagaki, Yusuke Nozaki, Masaya Yoshikawa · 2020
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.