The orchestrated manipulation of public opinion, particularly through manipulated images, often spread via online social networks (OSN), has become a serious threat to society. In this paper we introduce the Digital Forensics Net (DF-Net), a deep neural network for pixel-wise image forgery detection. The released model outperforms several state-of-the-art methods on four established benchmark datasets. Most notably, DF-Net's detection is robust against lossy image operations (e.g resizing, compression) as they are automatically performed by social networks.
@article{arxiv.2503.22398,
title = {DF-Net: The Digital Forensics Network for Image Forgery Detection},
author = {David Fischinger and Martin Boyer},
journal= {arXiv preprint arXiv:2503.22398},
year = {2025}
}
Comments
Published in 2023 at the 25th Irish Machine Vision and Image Processing Conference (IMVIP), https://iprcs.github.io/pdf/IMVIP2023_Proceeding.pdf