<p>Cyber threats have become a global concern, and attackers use more efficient, hidden, and destructive techniques. Traditional signature- and rule-based systems struggle to encounter these latest threats, exposing organizations facing severe risks to their financial well-being and national security risks. Although Artificial Intelligence (AI) provides techniques for detecting threats in real-time, its black-box nature introduces challenges related to trust, regulatory compliance, and interpretability, particularly in high-risk environments where decision transparency is critical. The black-box nature of AI systems in critical situations demands complete transparency and ease of interpretation for people to trust automated threat detection methods. In this research, the proposed Smart Sustainable Cybersecurity (SSC) model incorporates XAI to improve interpretability and assist in validating and improving threat classification models to reduce the number of false positives and make them more resistant to adversarial attacks. The proposed SSC-based XAI model had a high accuracy level of 99.65% and a low miss-rate of 0.35% compared to other approaches while offering greater transparency that may support resilience against adversarial behavior. While these results are promising, they are based on a controlled benchmark dataset and require further validation across diverse, real-world environments. This improves the detection of cyber threats and enhances the ability for intelligent, adaptive, and anticipative cyber defenses by minimizing false positives while advancing interpretability.</p>