EdgeDoc: Hybrid CNN-Transformer Model for Accurate Forgery Detection and Localization in ID Documents

TL;DR

EdgeDoc is a hybrid CNN-Transformer model that effectively detects and localizes forgery in ID documents by leveraging auxiliary noiseprint features, demonstrating superior performance in challenging datasets and competitions.

Contribution

The paper introduces EdgeDoc, a novel hybrid CNN-Transformer architecture with noiseprint features for improved forgery detection and localization in ID documents.

Findings

Outperforms baseline methods on FantasyID dataset

Achieved third place in ICCV 2025 DeepID Challenge

Demonstrates robustness in real-world forgery scenarios

Abstract

The widespread availability of tools for manipulating images and documents has made it increasingly easy to forge digital documents, posing a serious threat to Know Your Customer (KYC) processes and remote onboarding systems. Detecting such forgeries is essential to preserving the integrity and security of these services. In this work, we present EdgeDoc, a novel approach for the detection and localization of document forgeries. Our architecture combines a lightweight convolutional transformer with auxiliary noiseprint features extracted from the images, enhancing its ability to detect subtle manipulations. EdgeDoc achieved third place in the ICCV 2025 DeepID Challenge, demonstrating its competitiveness. Experimental results on the FantasyID dataset show that our method outperforms baseline approaches, highlighting its effectiveness in realworld scenarios. Project page : https://www.idiap. ch/paper/edgedoc/