A Framework to Allow a Third Party to Watermark Numerical Data in an Encrypted Domain while Preserving its Statistical Properties

TL;DR

This paper presents a secure, privacy-preserving framework enabling third-party watermarking of encrypted numerical data, ensuring statistical accuracy, data privacy, and watermark security against passive attacks.

Contribution

It introduces two irreversible watermarking algorithms that preserve statistical correctness and data privacy while securing watermark ownership in encrypted data.

Findings

Watermarking algorithms preserve statistical result correctness.

Framework enables watermark embedding in encrypted data.

Security against passive attacks is robust without compromising data usability.

Abstract

Watermarking data for source tracking applications by its owner can be unfair for recipients because the data owner may redistribute the same watermarked data to many users. Hence, each data recipient should know the watermark embedded in their data; however, this may enable them to remove it, which violates the watermark security. To overcome this problem, this research develops a framework that allows the cloud to watermark numerical data taking into consideration: the correctness of the results of selected statistics, data privacy, the recipient's right to know the watermark that is embedded in their data, and the security of the watermark against passive attacks. The proposed framework contains two irreversible watermarking algorithms, each can preserve the correctness of the results for certain statistical operations. To preserve data privacy, the framework allows the cloud to watermark data while it is encrypted. Furthermore, the framework robustifies the security of the chosen algorithms to nominate the cloud as the only neutral judge able to verify the data ownership even if other users know the watermark. The security is enhanced in a way that does not affect the data usability. The time complexity to find the watermark is $\mathcal{O}(\frac{n!}{r!(n-r)!})$.