Less is More: A privacy-respecting Android malware classifier using federated learning

Less is More: A privacy-respecting Android malware classifier using federated learning

In this paper we present LiM (‘Less is More’), a malware classification framework that leverages Federated Learning to detect and classify malicious apps in a privacy-respecting manner. Information about newly installed apps is kept locally on users’ devices, so that the provider cannot infer which...

Full description

Bibliographic Details
Main Authors: Gálvez Rafa, Moonsamy Veelasha, Diaz Claudia
Format: Article
Language:English
Published: Sciendo 2021-10-01
Series:Proceedings on Privacy Enhancing Technologies
Subjects:
android
malware detection
privacy
poisoning
integrity
federated learning
semi-supervised
machine learning
Online Access:https://doi.org/10.2478/popets-2021-0062

Internet

https://doi.org/10.2478/popets-2021-0062

Similar Items