The Securing Machine Learning Algorithms report presents a taxonomy of ML techniques and core functionalities. The report also includes a mapping of the threats targeting ML techniques and the vulnerabilities of ML algorithms. It provides a list of relevant security controls recommended to enhance cybersecurity in systems relying on ML techniques. One of the challenges highlighted is how to select the security controls to apply without jeopardising the expected level of performance.
Securing machine learning algorithms / C. Baylon, C. Berghoff, S. Brunessaux, L. Burdalo, G. D'Acquisto, E. Damiani, S. Herpig, C. Louveaux, J. Mistiaen, D. Cu Nguyen, N. Polemi, I. Praca, G. Sharkov, V. Slieker, E. Szczekocka ; [a cura di] A. Malatras, I. Agrafiotis, M. Adamczyk. - [s.l] : ENISA, 2021. - ISBN 978-92-9204-543-2.
Securing machine learning algorithms
E. Damiani;
2021
Abstract
The Securing Machine Learning Algorithms report presents a taxonomy of ML techniques and core functionalities. The report also includes a mapping of the threats targeting ML techniques and the vulnerabilities of ML algorithms. It provides a list of relevant security controls recommended to enhance cybersecurity in systems relying on ML techniques. One of the challenges highlighted is how to select the security controls to apply without jeopardising the expected level of performance.
| File | Dimensione | Formato | |
|---|---|---|---|
|
ENISA Report - Securing Machine Learning Algorithms.pdf
accesso aperto
Tipologia:
Publisher's version/PDF
Dimensione
2.62 MB
Formato
Adobe PDF
|
2.62 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
