Open Access

ARTICLE

Entropy-Based Watermarking Approach for Sensitive Tamper Detection of Arabic Text

Fahd N. Al-Wesabi^1,2,*
1 Department of Computer Science, King Khalid University, Muhayel Aseer, Kingdom of Saudi Arabia
2 Faculty of Computer and IT, Sana’a University, Sana’a, Yemen
* Corresponding Author: Fahd N. Al-Wesabi. Email:

Computers, Materials & Continua 2021, 67(3), 3635-3648. https://doi.org/10.32604/cmc.2021.015865

Received 11 December 2020; Accepted 11 January 2021; Issue published 01 March 2021

Abstract

The digital text media is the most common media transferred via the internet for various purposes and is very sensitive to transfer online with the possibility to be tampered illegally by the tampering attacks. Therefore, improving the security and authenticity of the text when it is transferred via the internet has become one of the most difficult challenges that researchers face today. Arabic text is more sensitive than other languages due to Harakat’s existence in Arabic diacritics such as Kasra, and Damma in which making basic changes such as modifying diacritic arrangements can lead to change the text meaning. In this paper, an intelligent hybrid solution is proposed with highly sensitive detection for any tampering on Arabic text exchanged via the internet. Natural language processing, entropy, and watermarking techniques have been integrated into this method to improve the security and reliability of Arabic text without limitations in text nature or size, and type or volumes of tampering attack. The proposed scheme is implemented, simulated, and validated using four standard Arabic datasets of varying lengths under multiple random locations of insertion, reorder, and deletion attacks. The experimental and simulation results prove the accuracy of tampering detection of the proposed scheme against all kinds of tampering attacks. Comparison results show that the proposed approach outperforms all of the other baseline approaches in terms of tampering detection accuracy.

---

Keywords

Entropy; text features; tamper detection; arabic text; NLP

---