International Journal of Applied Information Systems |
Foundation of Computer Science (FCS), NY, USA |
Volume 7 - Number 1 |
Year of Publication: 2014 |
Authors: Fadl M. Ba-alwi, Mokhtar M. Ghilan, Fahd N. Al-wesabi |
10.5120/ijais14-451128 |
Fadl M. Ba-alwi, Mokhtar M. Ghilan, Fahd N. Al-wesabi . Content Authentication of English Text via Internet using Zero Watermarking Technique and Markov Model. International Journal of Applied Information Systems. 7, 1 ( April 2014), 25-36. DOI=10.5120/ijais14-451128
In the study of content authentication and tamper detection of digital text documents, there are very limited techniques available for content authentication of text documents using digital watermarking techniques. A novel intelligent text zero watermarking approach based on probabilistic patterns has been proposed in this paper for content authentication and tamper detection of English text documents. In the proposed approach, Markov model of order THREE and letter-based was constructed and abbreviated as LNMZW3 for text analysis and utilizes the interrelationship between contents of given text to generate the watermark. However, we can extract this watermark later using extraction and detection algorithms to identify the status of text document such as authentic, or tampered. The proposed approach was implemented using PHP Programming language with Net Beans IDE 7. 0. Furthermore, the effectiveness and feasibility of our LNMZW3 approach has proved and compared with other recent approaches with experiments using five datasets of varying lengths and different volumes of attacks. Results show that the proposed approach is always detects tampering attacks occurred randomly on text even when the tampering volume is low, mid or high. Comparative results with the recent approaches shows that the our LNMZW3 approach provides added value under random insertion and deletion attacks in terms of performance, watermark robustness and watermark security. However, it is provide worst enhancement under reorder attacks.