Byzantine-robust federated learning via credibility assessment on non-IID data

<abstract> <p>Federated learning is a novel framework that enables resource-constrained edge devices to jointly learn a model, which solves the problem of data protection and data islands. However, standard federated learning is vulnerable to Byzantine attacks, which will cause the global model to be manipulated by the attacker or fail to converge. On non-iid data, the current methods are not effective in defensing against Byzantine attacks. In this paper, we propose a Byzantine-robust framework for federated learning via credibility assessment on non-iid data (BRCA). Credibility assessment is designed to detect Byzantine attacks by combing adaptive anomaly detection model and data verification. Specially, an adaptive mechanism is incorporated into the anomaly detection model for the training and prediction of the model. Simultaneously, a unified update algorithm is given to guarantee that the global model has a consistent direction. On non-iid data, our experiments demonstrate that the BRCA is more robust to Byzantine attacks compared with conventional methods.</p> </abstract>

Call to Arms

This article offers an edition, translation, and study of a hitherto unknown text about Ayyubid or early Mamluk Alexandria. The author, one Abū Khuzayma Muḥammad b. ʿAbd al-Wahhāb, gives a short yet rich description of the city based as much on Alexandria’s real cityscape as on legends. The text treats famous monuments, such as the city’s lighthouse and the Column of the Pillars, as well as less well-known buildings, such as mosques, colleges, watchtowers, and gates. An analysis of the account leads to the conclusion that its author wrote the account in order to mobilize Muslims for the defense of the city against Frankish or Byzantine attacks on Alexandria or Egypt’s Mediterranean coast in general.