FreqyWM: Frequency Watermarking for the New Data Economy

TL;DR

FreqyWM introduces a novel frequency-based watermarking technique for datasets, enabling ownership protection with robustness against attacks, applicable across various data types and marketplaces.

Contribution

The paper proposes a new frequency watermarking method for datasets, including algorithms for creation and verification, with analytical bounds and robustness analysis.

Findings

Robust against various attacks

Applicable to single and multidimensional datasets

Provides analytical bounds for false positive probability

Abstract

We present a novel technique for modulating the appearance frequency of a few tokens within a dataset for encoding an invisible watermark that can be used to protect ownership rights upon data. We develop optimal as well as fast heuristic algorithms for creating and verifying such watermarks. We also demonstrate the robustness of our technique against various attacks and derive analytical bounds for the false positive probability of erroneously detecting a watermark on a dataset that does not carry it. Our technique is applicable to both single dimensional and multidimensional datasets, is independent of token type, allows for a fine control of the introduced distortion, and can be used in a variety of use cases that involve buying and selling data in contemporary data marketplaces.