Explainable Artificial Intelligence (XAI) for Malware Analysis: A Survey of Techniques, Applications, and Open Challenges

TL;DR

This survey analyzes explainable ML in malware analysis, addressing the tension between detection accuracy and interpretability. It surveys a broad range of techniques, spanning transparent and opaque models, post-hoc explanations, and model-specific/global approaches, and organizes them around concrete malware domains (Windows PE, Android, PDF, Linux, hardware). Key contributions include a taxonomy of explainability methods, a consolidated review of XAI-enabled malware classification/detection across multiple platforms, and a discussion of open challenges such as dataset quality, hybrid analysis, and defense against adversarial threats. The work provides a structured resource to help researchers and practitioners bridge high detection performance with human-understandable explanations in cybersecurity.

Abstract

Machine learning (ML) has rapidly advanced in recent years, revolutionizing fields such as finance, medicine, and cybersecurity. In malware detection, ML-based approaches have demonstrated high accuracy; however, their lack of transparency poses a significant challenge. Traditional black-box models often fail to provide interpretable justifications for their predictions, limiting their adoption in security-critical environments where understanding the reasoning behind a detection is essential for threat mitigation and response. Explainable AI (XAI) addresses this gap by enhancing model interpretability while maintaining strong detection capabilities. This survey presents a comprehensive review of state-of-the-art ML techniques for malware analysis, with a specific focus on explainability methods. We examine existing XAI frameworks, their application in malware classification and detection, and the challenges associated with making malware detection models more interpretable. Additionally, we explore recent advancements and highlight open research challenges in the field of explainable malware analysis. By providing a structured overview of XAI-driven malware detection approaches, this survey serves as a valuable resource for researchers and practitioners seeking to bridge the gap between ML performance and explainability in cybersecurity.

Figures (6)

• Figure 1: Machine Learning-Based File Classification Techniques
• Figure 2: Explainable Machine Learning Concept
• Figure 3: Taxonomy for Explainable Machine Learning Techniques Inspired by belle2021principles, chou2022counterfactuals and arrieta2020explainable.
• Figure 4: Explainable Malware Classification and Detection Approaches
• Figure 5: Explainable Hardware Malware generation workflow pan2020hardware.