Next-Generation Lightweight Explainable AI for Cybersecurity: A Review on Transparency and Real-Time Threat Mitigation

Khulud Salem Alshudukhi^1,*, Sijjad Ali², Mamoona Humayun^3,*, Omar Alruwaili⁴
1 Department of Computer Science, College of Computer and Information Sciences, Jouf University, Sakaka, 72388, Al-Jouf, Saudi Arabia
2 College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China
3 School of Computing, Engineering and the Built Environment, University of Roehampton, London, SW155PJ, UK
4 Department of Computer Engineering and Networks, College of Computer and Information Sciences, Jouf University, Sakaka, 72388, Al-Jouf, Saudi Arabia
* Corresponding Author: Khulud Salem Alshudukhi. Email: email ; Mamoona Humayun. Email: email

Computer Modeling in Engineering & Sciences https://doi.org/10.32604/cmes.2025.073705

Received 24 September 2025; Accepted 30 October 2025; Published online 03 December 2025

Download PDF

Abstract

Problem: The integration of Artificial Intelligence (AI) into cybersecurity, while enhancing threat detection, is hampered by the “black box” nature of complex models, eroding trust, accountability, and regulatory compliance. Explainable AI (XAI) aims to resolve this opacity but introduces a critical new vulnerability: the adversarial exploitation of model explanations themselves. Gap: Current research lacks a comprehensive synthesis of this dual role of XAI in cybersecurity—as both a tool for transparency and a potential attack vector. There is a pressing need to systematically analyze the trade-offs between interpretability and security, evaluate defense mechanisms, and outline a path for developing robust, next-generation XAI frameworks. Solution: This review provides a systematic examination of XAI techniques (e.g., SHAP, LIME, Grad-CAM) and their applications in intrusion detection, malware analysis, and fraud prevention. It critically evaluates the security risks posed by XAI, including model inversion and explanation-guided evasion attacks, and assesses corresponding defense strategies such as adversarially robust training, differential privacy, and secure-XAI deployment patterns. Contribution: The primary contributions of this work are: (1) a comparative analysis of XAI methods tailored for cybersecurity contexts; (2) an identification of the critical trade-off between model interpretability and security robustness; (3) a synthesis of defense mechanisms to mitigate XAI-specific vulnerabilities; and (4) a forward-looking perspective proposing future research directions, including quantum-safe XAI, hybrid neuro-symbolic models, and the integration of XAI into Zero Trust Architectures. This review serves as a foundational resource for developing transparent, trustworthy, and resilient AI-driven cybersecurity systems.