Loading...
research article
Machine Learning Security Against Data Poisoning: Are We There Yet?
March 1, 2024
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.
Type
research article
Web of Science ID
WOS:001180702200002
Authors
Cina, Antonio Emanuele
•
•
Demontis, Ambra
•
Biggio, Battista
•
Roli, Fabio
•
Pelillo, Marcello
Publication date
2024-03-01
Publisher
Published in
Volume
57
Issue
3
Start page
26
End page
34
Peer reviewed
REVIEWED
EPFL units
Funder | Grant Number |
PRIN 2017 project RexLearn | |
Available on Infoscience
April 17, 2024
Use this identifier to reference this record