Litcius/Paper detail

Machine learning and hardware security

Francesco Regazzoni, Shivam Bhasin, Amir Ali Pour, Ihab Alshaer, Furkan Aydın, Aydın Aysu, Vincent Beroulle, Giorgio Di Natale, Paul D. Franzon, David Hély, Naofumi Homma, A. S. Ito, Dirmanto Jap, Priyank Kashyap, Ilia Polian, Seetal Potluri, Rei Ueno, Elena Ioana Vatajelu, Ville Yli-Mäyry

202020 citationsDOI

Abstract

Machine learning techniques have significantly changed our lives. They helped improving our everyday routines, but they also demonstrated to be an extremely helpful tool for more advanced and complex applications. However, the implications of hardware security problems under a massive diffusion of machine learning techniques are still to be completely understood. This paper first highlights novel applications of machine learning for hardware security, such as evaluation of post quantum cryptography hardware and extraction of physically unclonable functions from neural networks. Later, practical model extraction attack based on electromagnetic side-channel measurements are demonstrated followed by a discussion of strategies to protect proprietary models by watermarking them.

Topics & Concepts

Hardware security moduleComputer scienceCryptographyEmbedded systemFeature extractionDeep learningSide channel attackArtificial neural networkComputer engineeringDigital watermarkingMachine learningArtificial intelligenceComputer hardwareComputer securityImage (mathematics)Physical Unclonable Functions (PUFs) and Hardware SecurityAdvanced Malware Detection TechniquesAdversarial Robustness in Machine Learning
Machine learning and hardware security | Litcius