Machine Learning Security Against Data Poisoning: Are We There Yet?
2024
Abstract
Poisoning attacks compromise the training data utilized to train machine learning (ML) models, diminishing their overall performance, manipulating predictions on specific test samples, and implanting backdoors. This article thoughtfully explores these attacks while discussing strategies to mitigate them through fundamental security principles or by implementing defensive mechanisms tailored for ML.
Details
Title
Machine Learning Security Against Data Poisoning: Are We There Yet?
Author(s)
Cina, Antonio Emanuele ; Grosse, Kathrin ; Demontis, Ambra ; Biggio, Battista ; Roli, Fabio ; Pelillo, Marcello
Published in
Computer
Volume
57
Issue
3
Pages
26-34
Date
2024-03-01
Publisher
Los Alamitos, Ieee Computer Soc
ISSN
0018-9162
1558-0814
1558-0814
Keywords
Other identifier(s)
View record in Web of Science
Laboratories
VITA
Record Appears in
Scientific production and competences > ENAC - School of Architecture, Civil and Environmental Engineering > IIC - Civil Engineering Institute > VITA - Visual Intelligence for Transportation
Peer-reviewed publications
Work produced at EPFL
Journal Articles
Published
Peer-reviewed publications
Work produced at EPFL
Journal Articles
Published
Grant
PRIN 2017 project RexLearn
Record creation date
2024-04-17