Abnormal Local Clustering in Federated Learning
This addresses privacy and model integrity issues in federated learning for distributed systems, but appears incremental as it builds on existing clustering techniques.
The paper tackled the problem of identifying abnormal local clients in federated learning by using Euclidean similarity clustering on vectors from dummy data inputs, resulting in successful separation of normal and abnormal locals in a classification model.
Federated learning is a model for privacy without revealing private data by transfer models instead of personal and private data from local client devices. While, in the global model, it's crucial to recognize each local data is normal. This paper suggests one method to separate normal locals and abnormal locals by Euclidean similarity clustering of vectors extracted by inputting dummy data in local models. In a federated classification model, this method divided locals into normal and abnormal.