Trembling triggers: exploring the sensitivity of backdoors in DNN-based face recognition

Trembling triggers: exploring the sensitivity of backdoors in DNN-based face recognition

Abstract Backdoor attacks against supervised machine learning methods seek to modify the training samples in such a way that, at inference time, the presence of a specific pattern (trigger) in the input data causes misclassifications to a target class chosen by the adversary. Successful backdoor att...

Full description

Bibliographic Details
Main Authors: Cecilia Pasquini, Rainer Böhme
Format: Article
Language:English
Published: SpringerOpen 2020-06-01
Series:EURASIP Journal on Information Security
Subjects:
Backdoor attacks
Neural networks
Adversarial machine learning
Online Access:http://link.springer.com/article/10.1186/s13635-020-00104-z

Internet

http://link.springer.com/article/10.1186/s13635-020-00104-z

Similar Items