Abstract
We present a Federated Learning (FL) based solution for building a distributed classifier capable of detecting URLs containing sensitive content, i.e., content related to categories such as health, political beliefs, sexual orientation, etc. Although such a classifier addresses the limitations of previous offline/centralised classifiers, it is still vulnerable to poisoning attacks from malicious users that may attempt to reduce the accuracy for benign users by disseminating faulty model updates. To guard against this, we develop a robust aggregation scheme based on subjective logic and residual-based attack detection. Employing a combination of theoretical analysis, trace-driven simulation, as well as experimental validation with a prototype and real users, we show that our classifier can detect sensitive content with high accuracy, learn new labels fast, and remain robust in view of poisoning attacks from malicious users, as well as imperfect input from non-malicious ones.
Original language | English |
---|---|
Title of host publication | Securing Federated Sensitive Topic Classification against Poisoning Attacks |
Number of pages | 18 |
DOIs | |
Publication status | Published - 2023 |
Bibliographical note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-careOtherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.