Reversible and semi-blind relational database watermarking

In 2002, Agrawal and Kiernan proposed a relational database watermarking scheme that modifies least significant bits (LSBs) of numerical attributes selected using a secret key. The scheme does not address query preservation (some queries give different results when executed on the original and watermarked relation). Additive and secondary watermarking attacks on the watermarked relation are also possible. Such attacks can render the original watermark undetectable. Hence, an attacker who embeds his watermark in a previously watermarked relation can claim ownership of that relation. However, if the scheme is reversible, then a previous watermark, if any, can be detected in the reversed relation. In this paper, we propose an enhanced reversible, semi-blind and query-preserving watermarking scheme. Using this scheme, the correct owner of a relation can be identified even if the relation has been watermarked by multiple parties. If required, the database can be restored to it's original state too. This finds applications in high-precision settings such as military operations or scientific experiments.