MACHINE LEARNING-POWERED SECURITY FRAMEWORK FOR MALICIOUS ACTIVITIES DETECTION IN MOBILE EDGE COMPUTING

Abstract

Mobile Edge Computing (MEC) is a transformative paradigm that brings computation and data storage closer to end-users, thereby enhancing the performance of mobile applications. However, this decentralization introduces new security challenges, making MEC environments increasingly vulnerable to malicious activities such as data breaches, denial-of-service (DoS) attacks, and intrusion attempts. Traditional security mechanisms, primarily based on signature and rule-based detection systems, are limited in scope as they rely on predefined attack patterns, rendering them ineffective against novel and evolving threats. To overcome these limitations, machine learning (ML) techniques have emerged as powerful tools in securing mobile edge environments. ML-based systems can autonomously analyze vast volumes of data, identify patterns of abnormal behavior, and detect both known and unknown attacks in real-time. Despite their promise, early implementations of such systems faced challenges like high false-positive rates, limited generalization capabilities, and dependence on manual threat updates. This study proposes an intelligent, ML-driven security framework for MEC, leveraging classifiers such as Decision Trees, Random Forests, and Deep Neural Networks. These models offer improved detection accuracy, scalability, and adaptability by continuously learning from new data. By automating threat identification and response, the proposed framework enhances the integrity, availability, and confidentiality of mobile edge systems, paving the way for more resilient and secure computing at the network edge.