Enhanced Watermarking Scheme Using Formal Usability Constraints for Outsourced Dataset

Abstract

Watermarking is the commonly used mechanism to enforce and prove ownership for the digital data in different formats like audio, video, image, relational database, text and software. In the emerging field of “sharing datasets” with the intended, to protect ownership on the datasets is becoming a challenge in itself. The important challenge in watermarking datasets is usually, an owner needs to manually define "Usability constraints" for each type of dataset to preserve the contained knowledge. The novel formal model aims at preserve the knowledge in each attribute and other major characteristics of datasets that play an important role during the data mining process. The new watermark embedding algorithm to prove that the inserted watermark not only preserves the knowledge contained in a dataset but also significantly enhances watermark security in dataset. In insert watermark should be imperceptible and robust against any type of attacks.