PAC-X: Fuzzy Explainable AI for Multiclass Malware Detection
- 15 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 34 (1) , 53-64
Abstract
Researchers often approach malware detection as a binary classification problem. However, evidence indicates that malware can belong to multiple families simultaneously, and malicious files frequently exhibit numerous benign features. Attackers exploit this by embedding malicious intent within benign features, making malware detection a problem better suited for fuzzy systems. Furthermore, providing explainability for such fuzzy classification remains a significant challenge, requiring specialized Explainable AI (XAI) frameworks. Existing XAI approaches offer insights into model decisions but are vulnerable to adversarial attacks that manipulate features to mislead models. To address these issues, we propose PAC-X, a novel XAI framework for malware detection. PAC-X integrates the Conditional Attention Neural Network (CAN-Net) to deliver comprehensive multi-fuzzy-class explainability and employs Contextual Fuzzy Clustering (CFC) to extract contextual insights from training data. This framework is resilient to adversarial manipulations, maintaining reliable and interpretable explanations even under adversarial conditions designed to mislead the model. Through extensive evaluations on diverse malware datasets, PAC-X demonstrates superior explainability and robustness compared to state-of-the-art XAI methods. It provides a critical advancement in cybersecurity by addressing the complexities of evasive malware detection and enabling a deeper interpretation of multi-class malware characteristics.Keywords
Funding Information
- BlackBerry Limited (ALLRP 561035)
- Defence Research and Development Canada (W7701-217332)
- NSERC Alliance (ALLRP 561035-20)
- NSERC Discovery (RGPIN-2024-04087)
- NSERC CREATE (CREATE-554764-2021)
- Canada Research Chairs (CRC-2019-00041)
This publication has 32 references indexed in Scilit:
- PAIRED: An Explainable Lightweight Android Malware Detection SystemIEEE Access, 2022
- CFGExplainer: Explaining Graph Neural Network-Based Malware Classification from Control Flow Graphs2022
- “How Does It Detect A Malicious App?” Explaining the Predictions of AI-based Malware Detector2022
- Effective and Efficient Hybrid Android Malware Classification Using Pseudo-Label Stacked Auto-EncoderJournal of Network and Systems Management, 2021
- Learning Explainable Representations of Malware Behavior2021
- I-MAD: Interpretable malware detector using Galaxy TransformerComputers & Security, 2021
- Association rule-based malware classification using common subsequences of API callsApplied Soft Computing, 2021
- Towards Explainable CNNs for Android Malware DetectionProcedia Computer Science, 2021
- The Optimal Estimation of Fuzziness Parameter in Fuzzy C-Means Algorithm2017
- Cutting the Gordian Knot: A Look Under the Hood of Ransomware Attacks2015