This paper presents a decentralized AI-driven digital document forensics system that addresses critical limitations of existing centralized, rule-based verification frameworks. The proposed architecture integrates convolutional neural network (CNN)-based deep learning for accurate detection and localization of forged document regions, SHA-256 cryptographic hashing for tamper-evident integrity verification, and Ethereum blockchain smart contracts for immutable, non-repudiable evidence storage. A FastAPI-powered backend orchestrates interactions among the AI analysis module, the cryptographic layer, and the blockchain network, while a web-based frontend provides an accessible interface for document submission and result visualization. Experimental evaluation demonstrates the system’s effectiveness in detecting complex forgeries in real time, with a scalable, decentralized architecture that eliminates single points of failure. The proposed framework offers a practical and deployable solution for digital document authentication in legal, academic, financial, and governmental domains.
Panchetti et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: