FedMUP: Federated Learning driven Malicious User Prediction Model for Secure Data Distribution in Cloud Environments

TL;DR

FedMUP addresses cloud data security by proactively predicting malicious users through a federated learning framework that trains locally and aggregates updates to form a global model, minimizing raw data transfers. It combines a User Behavior Evaluation unit with a Malicious User Prediction unit to classify data-access requests in real time, using deep learning–based FL variants and averaging to update the global model. Empirical evaluation on the CMU CERT r4.2 insider-threat dataset shows FedMUP achieving superior accuracy, precision, recall, and F1-score over state-of-the-art baselines, while balancing privacy and performance. The work advances secure data distribution in cloud environments and points to adaptive privacy-preserving extensions as a path for future research.

Abstract

Cloud computing is flourishing at a rapid pace. Significant consequences related to data security appear as a malicious user may get unauthorized access to sensitive data which may be misused, further. This raises an alarm-ringing situation to tackle the crucial issue related to data security and proactive malicious user prediction. This article proposes a Federated learning driven Malicious User Prediction Model for Secure Data Distribution in Cloud Environments (FedMUP). This approach firstly analyses user behavior to acquire multiple security risk parameters. Afterward, it employs the federated learning-driven malicious user prediction approach to reveal doubtful users, proactively. FedMUP trains the local model on their local dataset and transfers computed values rather than actual raw data to obtain an updated global model based on averaging various local versions. This updated model is shared repeatedly at regular intervals with the user for retraining to acquire a better, and more efficient model capable of predicting malicious users more precisely. Extensive experimental work and comparison of the proposed model with state-of-the-art approaches demonstrate the efficiency of the proposed work. Significant improvement is observed in the key performance indicators such as malicious user prediction accuracy, precision, recall, and f1-score up to 14.32%, 17.88%, 14.32%, and 18.35%, respectively.

Figures (9)

• Figure 1: Operational viewpoint of the proposed FedMUP Model
• Figure 2: Architecture of proposed FedMUP Model
• Figure 3: Model Selection Approach
• Figure 4: Illustration for Classical vs FedMUP Model
• Figure 5: Design and Operational flow