paper-with-me

Papers

Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Key

2021-04-09 · MaungMaung AprilPyone, Hitoshi Kiya

In this paper, we propose a novel DNN watermarking method that utilizes a learnable image transformation method with a secret key. The proposed method embeds a watermark pattern in a model by using learnable transformed images and allows us to remotely verify the ownership of the model. As a result, it is piracy-resistant, so the original watermark cannot be overwritten by a pirated watermark, and adding a new watermark decreases the model accuracy unlike most of the existing DNN watermarking methods. In addition, it does not require a special pre-defined training set or trigger set. We empirically evaluated the proposed method on the CIFAR-10 dataset. The results show that it was resilient against fine-tuning and pruning attacks while maintaining a high watermark-detection accuracy.

📄 PDF Abstract BibTeX arXiv:2104.04241

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Robust Multi-bit Natural Language Watermarking through Invariant Features

2023-05-03 · KiYoon Yoo, Wonhyuk Ahn, Jiho Jang, Nojun Kwak

Recent years have witnessed a proliferation of valuable original natural language contents found in subscription-based media outlets, web novel platforms, and outputs of large language models. However, these contents are…

Evolutionary Trigger Set Generation for DNN Black-Box Watermarking

2019-06-11 · Jia Guo, Miodrag Potkonjak

The commercialization of deep learning creates a compelling need for intellectual property (IP) protection. Deep neural network (DNN) watermarking has been proposed as a promising tool to help model owners prove ownershi…

Piracy Resistant Watermarks for Deep Neural Networks

2019-10-02 · Huiying Li, Emily Wenger, Shawn Shan, Ben Y. Zhao 외

As companies continue to invest heavily in larger, more accurate and more robust deep learning models, they are exploring approaches to monetize their models while protecting their intellectual property. Model licensing …

Transfer Learning

CSGuard: Toward Forgery-Resistant Watermarking in Diffusion Models via Compressed Sensing Constraint

2026-05-02 · Jiewei Lai, Lan Zhang, Chen Tang, Pengcheng Sun 외 arxiv

Latent-based diffusion model watermarking embeds watermarks into generated images' latent space to enable content attribution, offering a training-free solution for intellectual property protection and digital forensics.…

Image Generation

ROMark: A Robust Watermarking System Using Adversarial Training

2019-10-02 · Bingyang Wen, Sergul Aydore

The availability and easy access to digital communication increase the risk of copyrighted material piracy. In order to detect illegal use or distribution of data, digital watermarking has been proposed as a suitable too…

BIG-bench Machine Learning