Deep Learning-based Forgery Attack on Document Images

TL;DR

This paper introduces a deep learning-based method for realistic document image forgery that effectively alters text while minimizing detectable traces, outperforming existing techniques in quality and fooling authentication systems.

Contribution

The work presents a novel deep learning framework that improves text editing on document images by addressing complex characters, backgrounds, and forgery trace mitigation, with practical attack demonstrations.

Findings

Reduces reconstruction error by about 66% compared to existing methods

Improves image quality metrics (PSNR and SSIM) by 4 dB and 0.21

Successfully fools document authentication systems with forged samples

Abstract

With the ongoing popularization of online services, the digital document images have been used in various applications. Meanwhile, there have emerged some deep learning-based text editing algorithms which alter the textual information of an image . In this work, we present a document forgery algorithm to edit practical document images. To achieve this goal, the limitations of existing text editing algorithms towards complicated characters and complex background are addressed by a set of network design strategies. First, the unnecessary confusion in the supervision data is avoided by disentangling the textual and background information in the source images. Second, to capture the structure of some complicated components, the text skeleton is provided as auxiliary information and the continuity in texture is considered explicitly in the loss function. Third, the forgery traces induced by the text editing operation are mitigated by some post-processing operations which consider the distortions from the print-and-scan channel. Quantitative comparisons of the proposed method and the exiting approach have shown the advantages of our design by reducing the about 2/3 reconstruction error measured in MSE, improving reconstruction quality measured in PSNR and in SSIM by 4 dB and 0.21, respectively. Qualitative experiments have confirmed that the reconstruction results of the proposed method are visually better than the existing approach. More importantly, we have demonstrated the performance of the proposed document forgery algorithm under a practical scenario where an attacker is able to alter the textual information in an identity document using only one sample in the target domain. The forged-and-recaptured samples created by the proposed text editing attack and recapturing operation have successfully fooled some existing document authentication systems.