A Systematic Literature Review on AI-Based Methods for Malware Detection

Abstract

Recent breakthroughs in artificial intelligence have improved malware detection, allowing systems to discover new threats by recognizing unexpected patterns that go beyond established signatures. AI-driven detection is critical in cybersecurity, and it covers malware detection, intrusion detection, and phishing prevention. This review investigates AI-based malware detection studies from (2015-2024) with a focus on machine learning and deep learning techniques. It emphasizes improvements in dealing with complex malware, including polymorphic and file less variants, while also highlighting obstacles like as high computing costs and data issues. The study emphasizes AI's potential for enhanced detection and encourages future research on real-time, resource-efficient, and interpretable models.