Digital Content Provenance and Anti-Forgery System: A Dual-Layered Framework for Secure Image Verification

Abstract

Advances in image editing tools and synthetic media generation have significantly increased the difficulty of distinguishing manipulated images from authentic visual content, thereby challenging the reliability of digital evidence. This work presents a Digital Content Provenance and Anti-Forgery System based on a dual-layer authentication strategy. The initial layer ex-amines provenance-related information through systematic analysis of image metadata to identify indications of post-processing and structural inconsistencies. The secondary layer applies visual forensic analysis based on compression residual patterns and supervised learning to identify manipulation artifacts that are not detectable through metadata inspection alone. The proposed approach is evaluated using a publicly available image tampering dataset and demonstrates effective discrimination between authentic and manipulated images, accompanied by statistically supported confidence measures. The results indicate that the integrated provenance and forensic framework support reliable image authentication in digital forensics and content verification scenarios.