A Robust and Reversible Watermarking Technique for Relational Dataset Based on Clustering

Chai, Heyan; Yang, Shuqiang; Jiang, Zoe L.; Wang, Xuan

doi:10.1109/trustcom/bigdatase.2019.00062

Cited by 5 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the collection of datasets is time-consuming and even expensive, all datasets deserve to be protected. Some techniques of dataset protection have been proposed, such as anonymization [9,10,11], encryption [12,13,14], and watermarking [15,16,17]. Their purposes are precluding unauthorized users to access the dataset.…”

Section: Introductionmentioning

confidence: 99%

Open-sourced Dataset Protection via Backdoor Watermarking

Li,

Zhang,

Bai

et al. 2020

Preprint

View full text Add to dashboard Cite

The rapid development of deep learning has benefited from the release of some high-quality open-sourced datasets (e.g., ImageNet), which allows researchers to easily verify the effectiveness of their algorithms. Almost all existing opensourced 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 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 dataset watermarking and dataset verification. We adopt classical poisoning-based backdoor attacks (e.g., BadNets) for dataset watermarking, i.e., generating some poisoned samples by adding a certain trigger (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., images with trigger) on the target class. Experiments on some benchmark datasets are conducted, which verify the effectiveness of the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

Open-sourced Dataset Protection via Backdoor Watermarking

Li,

Zhang,

Bai

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

Don’t Abandon the Primary Key: A High-Synchronization and Robust Virtual Primary Key Scheme for Watermarking Relational Databases

Yang,

Yuan,

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Comparative Analysis of Relational Database Watermarking Techniques: An Empirical Study

Rani

Halder

2022

IEEE Access

View full text Add to dashboard Cite

Digital watermarking is considered one of the most promising techniques to verify the authenticity and integrity of digital data. It is used for a wide range of applications, e.g., copyright protection, tamper detection, traitor tracing, maintaining the integrity of data, etc. In the past two decades, a wide range of algorithms for relational database watermarking has been proposed. Even though a number of surveys exist in the literature, they are unable to provide insightful guidance to choose the right watermarking technique for a given application. In this paper, we provide an exhaustive empirical study and thorough comparative analysis of various relational database watermarking techniques in the literature. Our work is different from the existing survey papers as we consider both distortion-based and distortion-free techniques along with a rigorous experimental analysis demonstrating a detailed comparison on robustness, data usability, and computational cost with considerable empirical evidence. INDEX TERMSDigital watermarking, relational database, empirical study, robustness, data usability. RAJU HALDER (Member, IEEE) received the Ph.D. degree from Università Ca´Foscari, Italy, in 2012. He is currently an Associate Professor with the Department of Computer Science and Engineering, IIT Patna. Before joining IIT Patna, he worked as a Postdoctoral Researcher with Macquarie University, Australia. He worked with the Robotics Team at HASLab (University of Minho), Portugal, in 2016. Prior to his Ph.D. degree, he had also worked as an Associate System Engineer at IBM India Private Ltd., from 2007 to 2008. His research interests include formal methods, blockchain technology, program analysis and verification, and data privacy and security.

show abstract

A Robust and Reversible Watermarking Technique for Relational Dataset Based on Clustering

Cited by 5 publications

References 21 publications

Open-sourced Dataset Protection via Backdoor Watermarking

Open-sourced Dataset Protection via Backdoor Watermarking

Don’t Abandon the Primary Key: A High-Synchronization and Robust Virtual Primary Key Scheme for Watermarking Relational Databases

Comparative Analysis of Relational Database Watermarking Techniques: An Empirical Study

Contact Info

Product

Resources

About