Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection

TL;DR

This paper proposes an untargeted backdoor watermarking scheme for datasets, enhancing copyright protection by avoiding targeted security risks and demonstrating effectiveness and robustness against defenses.

Contribution

It introduces an untargeted backdoor watermarking method for dataset ownership verification, addressing security issues of existing targeted approaches.

Findings

Effective watermarking on benchmark datasets

Resistant to existing backdoor defenses

Applicable in poisoned-label and clean-label settings

Abstract

Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets, based on which researchers and developers can easily evaluate and improve their learning methods. Since the data collection is usually time-consuming or even expensive, how to protect their copyrights is of great significance and worth further exploration. In this paper, we revisit dataset ownership verification. We find that existing verification methods introduced new security risks in DNNs trained on the protected dataset, due to the targeted nature of poison-only backdoor watermarks. To alleviate this problem, in this work, we explore the untargeted backdoor watermarking scheme, where the abnormal model behaviors are not deterministic. Specifically, we introduce two dispersibilities and prove their correlation, based on which we design the untargeted backdoor watermark under both poisoned-label and clean-label settings. We also discuss how to use the proposed untargeted backdoor watermark for dataset ownership verification. Experiments on benchmark datasets verify the effectiveness of our methods and their resistance to existing backdoor defenses. Our codes are available at \url{https://github.com/THUYimingLi/Untargeted_Backdoor_Watermark}.