Explainable Artificial Intelligence for Smart City Application: A Secure and Trusted Platform

Black-box AI poses security risks in smart cities: Traditional AI systems like deep learning lack interpretability, making it difficult to understand why they make decisions—a critical problem when these systems protect critical infrastructure in transportation, healthcare, and power systems where unexplained outputs could have serious consequences.

Explainability is essential for trustworthiness: The paper emphasizes that loss of control over how AI systems make decisions becomes a critical issue for automated applications, particularly in cybersecurity where understanding the reasoning behind threat detection or access denial is necessary for human operators to trust and validate system outputs.

XAI enables transition from "black-box to white-box": The paper advocates for Explainable Artificial Intelligence (XAI) as a solution to make AI decision-making transparent and interpretable, allowing stakeholders to understand not just what decisions are made, but why they are made.

Bias detection requires interpretability: The paper identifies that understanding AI bias and controlling for unexpected outputs is challenging with traditional AI, suggesting that explainability is necessary to identify and mitigate discriminatory or unfair decisions in smart city applications affecting citizens.

Multiple critical sectors depend on trustworthy AI: Smart city solutions across education, public governance, healthcare, and transportation increasingly rely on AI for data-driven decisions, making the security and interpretability of these systems essential for public safety and institutional accountability.