A Systematic Literature Review on AI-Based Methods and Challenges in Detecting Zero-Day Attacks

• Main Authors: Por, Lip Yee, Dai, Zhen, Leem, Siew Juan, Chen, Yi, Yang, Jing, Binbeshr, Farid, Yuen Phan, Koo, Soon Ku, Chin
• Format: Article
• Published: Institute of Electrical and Electronics Engineers 2024
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://eprints.um.edu.my/47128/; https://doi.org/10.1109/ACCESS.2024.3455410

The detection of zero-day attacks remains one of the most critical challenges in cybersecurity. This systematic literature review focuses on the various AI-based methods employed for detecting zero-day attacks, identifying both the strengths and weaknesses of these approaches. By critically evaluating existing literature, this review provides new insights and highlights the gaps that future research must address. The findings suggest that while artificial intelligence, particularly machine learning, offers promising solutions, there are significant challenges related to data availability, algorithmic complexity, and real-time application. This review contributes to the field by providing a comprehensive analysis of current AI-driven methods and proposing future research directions to enhance zero-day attack detection.