Genetic Algorithm Based Reversible Watermarking Approach For Relational Data

Abstract

Over the past few years, excessive growth in the
use of Internet has led to the generation and consumption of
huge amount of relational data. Relational databases is been
openly available within shared environment for knowledge gain
and decision making purposes to a large extent. To protect
these databases from various security attacks(insertion, deletion,
alteration, etc.,) and data tampering, watermarking techniques
are enforced. Reversible watermarking schemes are used to
impose ownership rights and tackling data tampering. But
these schemes are not robust against different active malicious
attacks and they modify the data content to a very large
extent resulting in data degradation. In this paper, a Genetic
Algorithm(GA) based robust and reversible watermarking(RRW)
technique for a numerical relational data is proposed which
ensures: i) recovery of the original relational data along with
the embedded watermark information and ii) achieve robustness
(attack resilience) in the presence of malicious attacks. Use of
Mutual Information(MI) concept along with genetic algorithm
enhances the process of watermarking relational database and
enables successful data recovery. Experimental studies proves the
effectiveness and performance of RRW against the attacks and
degradation in data quality.