HARNESSING ARTIFICIAL INTELLIGENCE FOR DDOS THREAT DETECTION AND MITIGATION TO STRENGTHEN RESILIENCE IN FINANCIAL AND EDUCATIONAL SYSTEMS

Abstract

This review explores the application of Artificial Intelligence (AI) techniques for detecting and mitigating Distributed Denial-of-Service (DDoS) attacks in financial and educational systems to enhance operational resilience. A DDoS attack overwhelms a target server, application, or network with excessive or maliciously crafted traffic originating from multiple distributed sources, thereby disrupting normal access for legitimate users. The escalating frequency and sophistication of DDoS attacks present a critical challenge to the stability of digital ecosystems, particularly within financial and educational systems that depend on uninterrupted online services. The risk is compounded by the growing availability of automated attack tools and the rising cyber curiosity among younger users, exposing these sectors to persistent threats. DDoS incidents can cripple essential services, causing financial losses, eroding digital trust, and disrupting learning and research  outcomes that undermine sustainable development goals in finance and education. Traditional static defense systems such as firewalls and access control lists (ACLs) have proven inadequate in countering these dynamic and large-scale threats. This review consolidates existing literature on AI-driven DDoS detection and mitigation approaches, including machine learning, deep learning, and hybrid models, highlighting their architectures, performance, and limitations. The study emphasizes the need for adaptive, intelligent, and context-aware defense mechanisms that leverage real-time analytics to protect financial and educational infrastructures. The paper concludes with a proposed conceptual AI-driven resilience framework and outlines future research directions to strengthen digital trust and operational continuity in critical sectors.