paper-with-me

홈 › Papers

From Image to Imuge: Immunized Image Generation

2021-10-27 · Qichao Ying, Zhenxing Qian, Hang Zhou, Haisheng Xu, Xinpeng Zhang, Siyi Li

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.

📄 PDF Abstract BibTeX arXiv:2110.14196

Code (1)

yingqichao/From-Image-to-Imuge-Immunized-Image-Generation 공식 구현 pytorch

Tasks

DecoderImage CroppingImage Generation

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
U-Net 설명 없음

Similar Papers 제목 키워드 기반

Learning to Immunize Images for Tamper Localization and Self-Recovery

2022-10-28 · Qichao Ying, Hang Zhou, Zhenxing Qian, Sheng Li 외

Digital images are vulnerable to nefarious tampering attacks such as content addition or removal that severely alter the original meaning. It is somehow like a person without protection that is open to various kinds of v…

Towards Transferable Defense Against Malicious Image Edits

2025-12-16 · Jie Zhang, Shuai Dong, Shiguang Shan, Xilin Chen arxiv

Recent approaches employing imperceptible perturbations in input images have demonstrated promising potential to counter malicious manipulations in diffusion-based image editing systems. However, existing methods suffer …

Image Editing

Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing

2025-09-27 · Rohit Chowdhury, Aniruddha Bala, Rohan Jaiswal, Siddharth Roheda arxiv

The rapid progress of image-to-video (I2V) generation models has introduced significant risks by enabling deceptive or malicious video synthesis from a single image. Prior defenses such as I2VGuard attempt to immunize im…

Adversarial DefenseMotion SynthesisVideo Generation

Multi-concept Model Immunization through Differentiable Model Merging

2024-12-19 · Amber Yijia Zheng, Raymond A. Yeh

Model immunization is an emerging direction that aims to mitigate the potential risk of misuse associated with open-sourced models and advancing adaptation methods. The idea is to make the released models' weights diffic…

model

Model Immunization from a Condition Number Perspective

2025-05-29 · Amber Yijia Zheng, Cedar Site Bai, Brian Bullins, Raymond A. Yeh

Model immunization aims to pre-train models that are difficult to fine-tune on harmful tasks while retaining their utility on other non-harmful tasks. Though prior work has shown empirical evidence for immunizing text-to…

model