The prosperity of machine learning has been accompanied by increasing attacks on the
training process. Among them, poisoning attacks have become an emerging threat during …

Anomaly detection has been used for decades to identify and extract anomalous
components from data. Many techniques have been used to detect anomalies. One of the …

Byzantine-robust federated learning aims to enable a service provider to learn an accurate
global model when a bounded number of clients are malicious. The key idea of existing …

Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep
neural networks in which participants' data remains on their own devices with only model …

Due to its decentralized nature, Federated Learning (FL) lends itself to adversarial attacks in
the form of backdoors during training. The goal of a backdoor is to corrupt the performance …

In federated learning, multiple client devices jointly learn a machine learning model: each
client device maintains a local model for its local training dataset, while a master device …

As data are increasingly being stored in different silos and societies becoming more aware
of data privacy issues, the traditional centralized training of artificial intelligence (AI) models …

Once users have shared their data online, it is generally difficult for them to revoke access
and ask for the data to be deleted. Machine learning (ML) exacerbates this problem because …

Lack of transparency in deep neural networks (DNNs) make them susceptible to backdoor
attacks, where hidden associations or triggers override normal classification to produce …

Deep neural networks and machine-learning algorithms are pervasively used in several
applications, ranging from computer vision to computer security. In most of these …