NL

Nikolaos Laoutaris

3 records found

MUDGUARD

Taming Malicious Majorities in Federated Learning using Privacy-preserving Byzantine-robust Clustering

Byzantine-robust Federated Learning (FL) aims to counter malicious clients and train an accurate global model while maintaining an extremely low attack success rate. Most existing systems, however, are only robust when most of the clients are honest. FLTrust (NDSS '21) and Zeno++ ...
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 t ...
In recent years, governments worldwide have moved their services online to better serve their citizens. Benefits aside, this choice increases the danger of tracking via such sites. This is of great concern as governmental websites increasingly become the only interaction point wi ...