SECURING WEB DATA WITH AUTOENCODERS: LITERATURE REVIEW ON DEEP LEARNING APPROACHES FOR ANOMALY DETECTION AND COMPRESSION

Abstract

Web security threats are increasing due to the rising complexity of cyber-attacks, prompting a shift from traditional rule-based systems to intelligent, adaptive solutions. This review examines current literature on anomaly detection and data compression techniques used in web data security. Emphasis is placed on the application of deep learning models, particularly autoencoders, for detecting abnormal web traffic patterns and improving data handling efficiency. The review explores recent advancements, challenges, and trends in integrating machine learning for real-time threat detection and secure data management. It also highlights research gaps and suggests future directions, including hybrid models and the potential role of emerging technologies such as reinforcement learning and blockchain.