Communication Dans Un Congrès Année : 2020

Machine Learning and Hardware security: Challenges and Opportunities

A. Ito

Résumé

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.

Fichier principal
Vignette du fichier
ICCAD_Paper.pdf (1.51 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-02999327 , version 1 (19-10-2021)

Licence

Identifiants

  • HAL Id : hal-02999327 , version 1

Citer

F. Regazzoni, S. Bhasin, Amir Ali Pour, Ihab Alshaer, F. Aydin, et al.. Machine Learning and Hardware security: Challenges and Opportunities. International Conference on Computer-Aided Design (ICCAD 2020), Nov 2020, San Diego, United States. ⟨hal-02999327⟩

Collections

399 Consultations
811 Téléchargements

Partager

  • More