A Taxonomy of Machine Learning Methodologies Used Against Physical Unclonable Functions
Seán Donnelly, Liam Meany · 2021
Recent research suggests that Physical Unclonable Functions (PUFs) will be a useful security tool for the Internet of Things. However, PUFs are vulnerable to many known machine learning attacks which threaten their effectiveness. This paper presents a unique taxonomy of known machine learning attacks and exploits against PUFs. In doing so, it offers a balanced and comprehensive evaluation, which will serve as an invaluable single point of reference for those undertaking research in this area.