On Implementation-Level Security of Edge-Based Machine Learning Models

Autor: Batina, L., Bhasin, S., Breier, J., Hou, X., Jap, D., Bäck, T., Buhan, I., Picek, S.

Publikováno v: Lecture notes in compute science ; 13049, 335-359. Cham : Springer International Publishing
STARTPAGE=335;ENDPAGE=359;TITLE=Lecture notes in compute science ; 13049

In this chapter, we are considering the physical security of Machine Learning (ML) implementations on Edge Devices. We list the state-of-the-art known physical attacks, with the main attack objectives to reverse engineer and misclassify ML models. Th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::8326ae67b1e5b7c61c6ceba7256c722b
http://hdl.handle.net/2066/250790

Machine Learning and Hardware security: Challenges and Opportunities: Invited Talk

Autor: Regazzoni, F., Bhasin, S., Pour, A.A., Alshaer, I., Aydin, F., Aysu, A., Beroulle, V., Di Natale, G., Franzon, P., Hely, D., Homma, N., Ito, A., Jap, D., Kashyap, P., Polian, I., Potluri, S., Ueno, R., Vatajelu, E.-I., Yli-Mäyry, V.

Publikováno v: 2020 IEEE/ACM International Conference on Computer-Aided Design (ICADD): digest of technical papers : November 2-5, 2020: virtual conference
2020 IEEE/ACM International Conference on Computer-Aided Design (ICADD)

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 hardwar

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=narcis______::fe842b7c2fedb0dddad6a01281b776a6
https://dare.uva.nl/personal/pure/en/publications/machine-learning-and-hardware-security-challenges-and-opportunities(32ea7986-4687-4f44-ac21-8fdda252613c).html

CSI NN: Reverse Engineering of Neural Network Architectures Through Electromagnetic Side Channel

Autor: Batina, L., Bhasin, S., Jap, D., Picek, S.

Publikováno v: CSI NN: Reverse Engineering of Neural Network Architectures Through Electromagnetic Side Channel, 1-19. USENIX
STARTPAGE=1;ENDPAGE=19;TITLE=CSI NN: Reverse Engineering of Neural Network Architectures Through Electromagnetic Side Channel
Proceedings of the 28th USENIX Security Symposium
CSI NN: Reverse Engineering of Neural Network Architectures Through Electromagnetic Side Channel, pp. 1-19

Machine learning has become mainstream across industries. Numerous examples prove the validity of it for security applications. In this work, we investigate how to reverse engineer a neural network by using side-channel information such as timing and

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::6636da7a19286695a207be85b56dd0dd
http://hdl.handle.net/2066/207790

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.