8 March 2024 in Journal of the Brazilian Computer Society
There is a exponential growth of data usage, specially due to the proliferation of connected applications with personalized models for different applications. In this context, Federated Learning (FL) emerges as a promising solution to enable collaborative model training while preserving the privacy and autonomy of participating clients. In a typical FL scenario, clients exhibit significant heterogeneity in terms of data distribution and hardware configurations. In this way, randomly sampling clients in each training round may not fully exploit the local updates from heterogeneous clients, resulting in lower model accuracy, slower convergence rate, degraded fairness, etc. In addition, malicious users could disseminate incorrect weights, which may decrease the accuracy of aggregated models and increase the time for convergence in FL. In this article, we introduce Resilience-aware Client Selection Mechanism for non-IID data and malicious clients in FL environment, called RICA. The proposed mechanism employs data size and entropy as criteria for client selection. In addition, RICA relies Centroid-Based Kernel Alignment (CKA) to identify and exclude potentially malicious clients. Our evaluation shows an improvement of 125% in Accuracy values in a scenario of malicious clients, which means the RICA+CKA demonstrates a more stable and resilient approach, reaching 90% accuracy in a few rounds compared to the default average approach, reached only around 30%. Therefore, results of the behavior of RICA+CKA in different datasets show the evaluation of different numbers of clients reaching around 90% while the other approach does not pass the 50% Accuracy.
4 March 2024 in Journal of Internet Services and Applications
Integrating big data and deep learning across various applications has significantly enhanced intelligence and efficiency in our daily lives. However, it also requires extensive data sharing, raising significant communication and privacy concerns. In this context, Federated Learning (FL) emerges as a promising solution to enable collaborative model training while preserving the privacy and autonomy of participating clients. FL facilitates collaborative model training by enabling data to be trained locally on devices, eliminating the need for individual information sharing among clients. A client selection mechanism strategically chooses a subset of participating clients to contribute to the model training in each learning round. However, an efficient selection of clients to participate in the training process directly impacts model convergence/accuracy and the overall communication load on the network. In addition, FL faces challenges when dealing with non-Independent and Non-Identically Distributed (non-IID) data, where the diversity in data distribution often leads to reduced classification accuracy. Hence, designing an efficient client selection mechanism in a scenario with non-IID data is essential, but it is still an open issue. This article proposes a Model Efficiency through Selective Federated Learning Algorithm called MESFLA. The mechanism employs a Centered Kernel Alignment (CKA) algorithm to search for similar models based on data weight or similarity between models, i.e., grouping participants with comparable data distributions or learning objectives. Afterward, MESFLA selects the clients with more relevance in each group based on data weight and entropy. Our comprehensive evaluation across multiple datasets, including MNIST, CIFAR-10, and CIFAR-100, demonstrates MESFLA's superior performance over traditional FL algorithms. Our results show an accuracy improvement and a minor loss in each client aggregation of the new global model sent to clients with a difference of 3 rounds using the Data Weight in comparison with the other selection methods.
9 January 2026 in Journal of Internet Services and Applications
Federated Learning (FL) is a machine learning training method that uses a collaborative model for training across a diverse set of clients, while preserving data privacy in accordance with the General Data Protection Regulation (GDPR) for clients' data. The classification and similarity within many clients can become an issue, often leading to decreased model accuracy and slower convergence, or reducing the number of parameters to the point of not learning anything during aggregation. However, the presence of non-IID data and malicious clients poses significant challenges to the significance of generalization models and distribution data. Malicious clients can perform poisoning attacks by sending harmful model updates that degrade the performance of the global model. This article introduces MONZA, a scoring system designed to detect and exclude malicious clients in FL environments. In a scenario where clients can also engage in various attacks, including model poisoning and data poisoning, this can lead to incorrect training. The proposed method uses cosine similarity to calculate client scores. It employs L2 normalization to identify biased models; in some cases, the similarity is not sufficient to classify a client, effectively filtering out malicious participants before aggregation and implementing a penalty with a quarentine method. Our evaluation shows that MONZA achieves an accuracy of 54.5% in a scenario with 30% malicious clients, while zPROBE (i.e., existing resilient methods) only reached an accuracy of 50%. Furthermore, MONZA reduces the simulation execution time by 66% and the computational effort to 83 MFLOP/s compared to zPROBE, which demonstrates to be a more efficient and resilient method. These results confirm that MONZA maintains the integrity of the model, making a security aggregation while minimizing resource consumption in malicious FL settings.