A Survey on ML Techniques for Multi-Platform Malware Detection: Securing PC, Mobile Devices, IoT, and Cloud...

Area of Science:

• Computer Science
• Cybersecurity
• Artificial Intelligence

Background:

• Malware poses a significant global threat, causing billions in financial losses.
• Cybercriminals exploit evolving malware capabilities across diverse platforms like PCs, mobile, IoT, and cloud.
• Existing research primarily focuses on single-platform malware detection, lacking a comprehensive cross-platform review.

Purpose of the Study:

• To provide an extensive review of machine learning (ML) techniques for malware detection across multiple platforms.
• To address the research gap in understanding and countering cross-platform malware threats.
• To motivate future research in adaptable, cross-platform malware detection.

Main Methods:

• Comprehensive literature review of ML-based malware detection since 2017.
• Analysis of malware detection techniques for PC, mobile, IoT, and cloud environments.
• Identification of current challenges and future research directions.

Main Results:

• Identified a lack of holistic, cross-platform malware detection strategies in existing research.
• Detailed the evolution of malware threats targeting diverse digital ecosystems.
• Synthesized recent advancements in ML for malware detection across platforms.

Conclusions:

• A platform-based understanding of malware detection is crucial for effective defense.
• Developing adaptable, cross-platform ML techniques is essential for future cybersecurity.
• This review provides a foundation for robust, evolving malware detection strategies.