The rapid growth of Internet of Things (IoT) devices presents significant cybersecurity challenges due to their diverse and resource-constrained nature. Existing security solutions often fall short in addressing the dynamic and distributed environments of IoT systems. This study aims to propose a novel deep learning framework, SecEdge, designed to enhance real-time cybersecurity in mobile IoT environments. The SecEdge framework integrates transformer-based models for efficient handling of long-range dependencies and Graph Neural Networks (GNNs) for modeling relational data, coupled with federated learning to ensure data privacy and reduce latency. The adaptive learning mechanism continuously updates model parameters to counter evolving cyber threats. The framework's performance was evaluated in a simulation environment using the NSL-KDD, UNSW-NB15, and CICIDS2017 datasets. Results demonstrated that SecEdge outperformed state-of-the-art methods with a detection rate of 98.8% for DoS attacks on NSL-KDD, 98.5% for MitM attacks on UNSW-NB15, and 98.7% for data injection attacks on CICIDS2017.

Class imbalance poses a significant challenge to supervised classification, particularly in critical domains like medical diagnostics and anomaly detection where minority class instances are rare. While numerous studies have explored rebalancing techniques to address this issue, less attention has been given to evaluating the performance of binary classifiers under imbalance when no such techniques are applied. Therefore, the goal of this study is to assess the performance of binary classifiers "as-is", without performing any explicit rebalancing. Specifically, we systematically evaluate the robustness of a diverse set of binary classifiers across both real-world and synthetic datasets, under progressively reduced minority class sizes, using one-shot and few-shot scenarios as baselines. Our approach also explores varying data complexities through synthetic decision boundary generation to simulate real-world conditions. In addition to standard classifiers, we include experiments using undersampling, oversampling strategies, and one-class classification (OCC) methods to examine their behavior under severe imbalance. The results confirm that classification becomes more difficult as data complexity increases and the minority class size decreases. While traditional classifiers deteriorate under extreme imbalance, advanced models like TabPFN and boosting-based ensembles retain relatively higher performance and better generalization compared to traditional classifiers. Visual interpretability and evaluation metrics further validate these findings. Our work offers valuable guidance on model selection for imbalanced learning, providing insights into classifier robustness without dependence on explicit rebalancing techniques.