Abstract :

The Rapid Advancement Of Artificial Intelligence Has Led To A Significant Increase In The Generation Of Synthetic Images Across Social Media, Journalism, Advertising, And Digital Communication Platforms. While AI-generated Images Offer Numerous Benefits, They Also Pose Serious Challenges Related To Misinformation, Identity Misuse, Digital Trust, And Content Authenticity. Traditional Image Verification Methods Based On Human Visual Inspection, Metadata Analysis, And Forensic Examination Are Often Subjective, Time-consuming, And Ineffective Against Highly Realistic Synthetic Content. To Address These Limitations, This Paper Presents An Automated AI-generated Image Detection Framework Based On Convolutional Neural Networks (CNNs) And Explainable Artificial Intelligence (XAI). The Proposed System Is Trained Using Real Images From The CIFAR-10 Dataset And Synthetic Images From The CIFAKE Dataset To Learn Discriminative Visual Features That Distinguish Authentic Images From AI-generated Counterparts. The CNN Model Performs Binary Classification, Identifying Images As Either Real Or Fake With High Accuracy And Efficiency. Furthermore, Explainable AI Techniques Provide Visual Interpretations Of Model Decisions, Enhancing Transparency And User Trust. Experimental Results Demonstrate That The Proposed Approach Effectively Detects Synthetic Images While Reducing Analysis Time And Improving Scalability Compared To Manual Methods. The Framework Contributes To Strengthening Digital Content Verification, Supporting Reliable Media Authentication, And Promoting Trustworthiness In Modern Digital Ecosystems.

Published:

07-6-2026

Issue:

Vol. 26 No. 6 (2026)

Page Nos:

379-384

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite