A zero-watermarking algorithm for text documents based on structural components

Advances in communication technologies have made it easier to distribute and communicate information effectively. The world has become a global village with the advent of the Internet. Besides getting the benefits of information technology, the world faces threats of violations of copyright, digital counterfeiting, privacy and plagiarism. These issues have been addressed for image, audio and video by researchers in the past, but the protection of copyright for plain text has been neglected. In this paper, we have proposed a novel zero-watermarking algorithm for authentication and copyright protection of text documents. The algorithm is robust against content-preserving modifications and at the same time, is capable of detecting malicious tampering. The experimental results demonstrate the effectiveness of the algorithm against random tampering attacks by calculating normalized absolute error of original and extracted watermark. The results are also compared to recent work in this domain.