TY - JOUR
T1 - Machine Learning and Hardware security
T2 - 39th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2020
AU - Regazzoni, Francesco
AU - Bhasin, Shivam
AU - Pour, Amir Ali
AU - Alshaer, Ihab
AU - Aydin, Furkan
AU - Aysu, Aydin
AU - Beroulle, Vincent
AU - Di Natale, Giorgio
AU - Franzon, Paul
AU - Hely, David
AU - Homma, Naofumi
AU - Ito, Akira
AU - Jap, Dirmanto
AU - Kashyap, Priyank
AU - Polian, Ilia
AU - Potluri, Seetal
AU - Ueno, Rei
AU - Vatajelu, Elena Ioana
AU - Yli Maeyry, Ville Oskari
N1 - Funding Information:
This work was performed in the Cooperative Research Project of the Research Institute of Electrical Communication, Tohoku University with Nanyang Technological University. This research is supported in part by the NSF under the Grants No. CNS 16-244770 (Center for Advanced Electronics through Machine Learning), by JST CREST Grant No.jPMjCR19KS,]apan, and by European Union's Horizon 2020 research and innovation programme CPSoSaware (grant agreement No 871738). The authors thank Paolo Palmieri and Dado Smailbegovic for the fruitful discussion about protection ofmachine learning algorithms.
Publisher Copyright:
© 2020 Association on Computer Machinery.
PY - 2020/11/2
Y1 - 2020/11/2
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85097934656&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097934656&partnerID=8YFLogxK
U2 - 10.1145/3400302.3416260
DO - 10.1145/3400302.3416260
M3 - Conference article
AN - SCOPUS:85097934656
SN - 1092-3152
VL - 2020-November
JO - IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers
JF - IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers
M1 - 9256522
Y2 - 2 November 2020 through 5 November 2020
ER -