English

Open-sourced Dataset Protection via Backdoor Watermarking

Cryptography and Security 2020-11-20 v3 Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning

Abstract

The rapid development of deep learning has benefited from the release of some high-quality open-sourced datasets (e.g.e.g., ImageNet), which allows researchers to easily verify the effectiveness of their algorithms. Almost all existing open-sourced datasets require that they can only be adopted for academic or educational purposes rather than commercial purposes, whereas there is still no good way to protect them. In this paper, we propose a \emph{backdoor embedding based dataset watermarking} method to protect an open-sourced image-classification dataset by verifying whether it is used for training a third-party model. Specifically, the proposed method contains two main processes, including \emph{dataset watermarking} and \emph{dataset verification}. We adopt classical poisoning-based backdoor attacks (e.g.e.g., BadNets) for dataset watermarking, ie, generating some poisoned samples by adding a certain trigger (e.g.e.g., a local patch) onto some benign samples, labeled with a pre-defined target class. Based on the proposed backdoor-based watermarking, we use a hypothesis test guided method for dataset verification based on the posterior probability generated by the suspicious third-party model of the benign samples and their correspondingly watermarked samples (i.e.i.e., images with trigger) on the target class. Experiments on some benchmark datasets are conducted, which verify the effectiveness of the proposed method.

Keywords

Cite

@article{arxiv.2010.05821,
  title  = {Open-sourced Dataset Protection via Backdoor Watermarking},
  author = {Yiming Li and Ziqi Zhang and Jiawang Bai and Baoyuan Wu and Yong Jiang and Shu-Tao Xia},
  journal= {arXiv preprint arXiv:2010.05821},
  year   = {2020}
}

Comments

Accepted by the NeurIPS Workshop on Dataset Curation and Security, 2020. 6 pages

R2 v1 2026-06-23T19:17:00.249Z