Trustworthy XAI and Application
MD Abdullah Al Nasim, A. S. M Anas Ferdous, Abdur Rashid, Fatema Tuj Johura Soshi, Parag Biswas, Angona Biswas, Kishor Datta Gupta
TL;DR
The paper addresses the problem of AI's opaque decision-making by surveying Explainable Artificial Intelligence (XAI) and its role in achieving trustworthy AI. It clarifies core concepts—transparency, explainability, and trustworthiness—while contrasting them with traditional AI and outlining how XAI can support security frameworks like Zero Trust Architecture. Through domain-focused discussions in healthcare, autonomous systems, and industry, it catalogs methods (transparent vs post-hoc), highlights regulatory and ethical considerations (FAT-ML), and presents real-world applications and future directions, including interactive explanations and human-centered design. The contribution lies in synthesizing definitions, classifications, and practical guidelines, offering a roadmap for building transparent, accountable AI systems with tangible impact for developers, regulators, and practitioners alike.
Abstract
Artificial Intelligence (AI) is an important part of our everyday lives. We use it in self-driving cars and smartphone assistants. People often call it a "black box" because its complex systems, especially deep neural networks, are hard to understand. This complexity raises concerns about accountability, bias, and fairness, even though AI can be quite accurate. Explainable Artificial Intelligence (XAI) is important for building trust. It helps ensure that AI systems work reliably and ethically. This article looks at XAI and its three main parts: transparency, explainability, and trustworthiness. We will discuss why these components matter in real-life situations. We will also review recent studies that show how XAI is used in different fields. Ultimately, gaining trust in AI systems is crucial for their successful use in society.