Title: Explainable AI for deepfake detection: strategies to mitigate bias and enhance trustworthiness

Authors: Neenu Maria Thankachan; Greeshma Kanakkassery Vijayaraghavan; Archana Sunil; Binshad Mangalath Nikarthil Shereef

Addresses: DefenAI PVT LMTD., Coimbatore, Tamil Nadu. India ' Computer Science, PSGR Krishnammal College for Women, Coimbatore, Tamil Nadu, India ' Forensic Science, Nehru Arts and Science College, Coimbatore, Tamil Nadu, India ' Forensic Science, Centre for Integrated Studies, CUSAT, Cochin-22, Kerala, India

Abstract: Deepfakes, hyper-realistic synthetic media, pose significant challenges by depicting individuals in situations they never experienced. While AI-powered deepfake detection methods show promise, they are prone to bias, affecting the authenticity and fairness of outcomes. This study explores the role of explainable AI (XAI) in reducing bias in deepfake detection systems. We analyse bias sources, including data and algorithmic biases, and propose strategies to mitigate them using XAI techniques like LIME and SHAP. We demonstrate how XAI enhances transparency, facilitates bias detection, and promotes fairer deepfake detection outcomes. Our research underscores the ethical implications of AI and the need for trustworthy AI systems to ensure societal well-being. This work contributes to the development of more effective and trustworthy deepfake detection mechanisms.

Keywords: artificial intelligence; datasets; deepfake; XAI; AI-generated images; Generative AI.

DOI: 10.1504/IJAISC.2025.149623

International Journal of Artificial Intelligence and Soft Computing, 2025 Vol.9 No.2, pp.164 - 177

Received: 30 Sep 2024
Accepted: 21 Jul 2025
Published online: 07 Nov 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article