We introduce Imuge, an image tamper resilient generative scheme for image self-recovery. The traditional manner of concealing image content within the image are inflexible and fragile to diverse digital attack, i.e. image cropping and JPEG compression. To address this issue, we jointly train a U-Net backboned encoder, a tamper localization network and a decoder for image recovery. Given an original image, the encoder produces a visually indistinguishable immunized image. At the recipient's side, the verifying network localizes the malicious modifications, and the original content can be approximately recovered by the decoder, despite the presence of the attacks. Several strategies are proposed to boost the training efficiency. We demonstrate that our method can recover the details of the tampered regions with a high quality despite the presence of various kinds of attacks. Comprehensive ablation studies are conducted to validate our network designs.
Cite
@article{arxiv.2110.14196,
title = {From Image to Imuge: Immunized Image Generation},
author = {Qichao Ying and Zhenxing Qian and Hang Zhou and Haisheng Xu and Xinpeng Zhang and Siyi Li},
journal= {arXiv preprint arXiv:2110.14196},
year = {2021}
}
Comments
Accepted as Poster at ACMMM 2021. Authors are from Fudan University, Simon Fraser University and NVIDIA, China