Enhancing fragility of zero-based text watermarking utilizing effective characters list

Saba, Tanzila; Bashardoost, Morteza; Kolivand, Hoshang; Rahim, Mohd Shafry Mohd; Rehman, Amjad; Khan, Muhammad Attique

doi:10.1007/s11042-019-08084-0

Cited by 11 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies [29][30][31] have used various machine learning algorithms such as support vector machines [32], decision trees [33], and deep neural networks [34] to address this problem. In recent years, CNNs have emerged as a popular approach for authorship verification due to their ability to learn complex features from textual data [35][36][37][38][39][40]. One of the earliest studies [39] using CNNs for authorship verification.…”

Section: Related Workmentioning

confidence: 99%

Hyper-Tuned Convolutional Neural Networks for Authorship Verification in Digital Forensic Investigations

Rahim,

Zhong,

Ahmad

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Authorship verification is a crucial task in digital forensic investigations, where it is often necessary to determine whether a specific individual wrote a particular piece of text. Convolutional Neural Networks (CNNs) have shown promise in solving this problem, but their performance highly depends on the choice of hyperparameters. In this paper, we explore the effectiveness of hyperparameter tuning in improving the performance of CNNs for authorship verification. We conduct experiments using a Hyper Tuned CNN model with three popular optimization algorithms: Adaptive Moment Estimation (ADAM), Stochastic Gradient Descent (SGD), and Root Mean Squared Propagation (RMSPROP). The model is trained and tested on a dataset of text samples collected from various authors, and the performance is evaluated using accuracy, precision, recall, and F1 score. We compare the performance of the three optimization algorithms and demonstrate the effectiveness of hyperparameter tuning in improving the accuracy of the CNN model. Our results show that the Hyper Tuned CNN model with ADAM Optimizer achieves the highest accuracy of up to 90%. Furthermore, we demonstrate that hyperparameter tuning can help achieve significant performance improvements, even using a relatively simple model architecture like CNNs. Our findings suggest that the choice of the optimization algorithm is a crucial factor in the performance of CNNs for authorship verification and that hyperparameter tuning can be an effective way to optimize this choice. Overall, this paper demonstrates the effectiveness of hyperparameter tuning in improving the performance of CNNs for authorship verification in digital forensic investigations. Our findings have important implications for developing accurate and reliable authorship verification systems, which are crucial for various applications in digital forensics, such as identifying the author of anonymous threatening messages or detecting cases of plagiarism.

show abstract

Section: Related Workmentioning

confidence: 99%

Hyper-Tuned Convolutional Neural Networks for Authorship Verification in Digital Forensic Investigations

Rahim,

Zhong,

Ahmad

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…Groundbreaking advances and research have been performed in AI related to text [6,7]. The English Language, including Dialog systems and Conversational Agents [8,9] are the major aspects. But when it comes to other languages, one argument put forward is that; Can the expertise obtained in the English Language be transferred to other resource-poor languages?…”

Section: Introductionmentioning

confidence: 99%

An Artificial Intelligence Approach for Word Semantic Similarity Measure of Hindi Language

2021

KSII TIIS

View full text Add to dashboard Cite

AI combined with NLP techniques has promoted the use of Virtual Assistants and have made people rely on them for many diverse uses. Conversational Agents are the most promising technique that assists computer users through their operation. An important challenge in developing Conversational Agents globally is transferring the groundbreaking expertise obtained in English to other languages. AI is making it possible to transfer this learning. There is a dire need to develop systems that understand secular languages. One such difficult language is Hindi, which is the fourth most spoken language in the world. Semantic similarity is an important part of Natural Language Processing, which involves applications such as ontology learning and information extraction, for developing conversational agents. Most of the research is concentrated on English and other European languages. This paper presents a Corpus-based word semantic similarity measure for Hindi. An experiment involving the translation of the English benchmark dataset to Hindi is performed, investigating the incorporation of the corpus, with human and machine similarity ratings. A significant correlation to the human intuition and the algorithm ratings has been calculated for analyzing the accuracy of the proposed similarity measures. The method can be adapted in various applications of word semantic similarity or module for any other language.

show abstract

“…This watermark can be extracted to provide proof of ownership. Zero based text watermarking using Effective Characters List (ECL) is proposed by Saba et al (2020).…”

Section: Introductionmentioning

confidence: 99%

Markov Matrix and Entropy based Tamper Detection Technique for Text Images

Singh

Sharma

2021

JER is an international, peer-reviewed journal that publishes f

View full text Add to dashboard Cite

In this paper, a novel watermarking technique for the tamper detection of text images is pro- posed. Entropy of every sentence is computed and Markov matrix using the occurrences of the characters is used to generate a character pattern. Entropy and character patterns are converted to Unicode Zero Width Characters (ZWCs) by using a lookup table. The ZWCs of entropy of each sentence is embedded at the end of every sentence after terminator. ZWCs of the character patterns are embedded in the end of the text of the image. On receiver side, ZWCs are extracted and converted to numerical form using the same lookup table. Entropy of every sentence and character patterns are recalculated and compared with extracted values for tamper detection. Comparison of technique with existing state-of-art techniques shows the effectiveness of the proposed technique.

show abstract

Enhancing fragility of zero-based text watermarking utilizing effective characters list

Cited by 11 publications

References 27 publications

Hyper-Tuned Convolutional Neural Networks for Authorship Verification in Digital Forensic Investigations

Hyper-Tuned Convolutional Neural Networks for Authorship Verification in Digital Forensic Investigations

An Artificial Intelligence Approach for Word Semantic Similarity Measure of Hindi Language

Markov Matrix and Entropy based Tamper Detection Technique for Text Images

Contact Info

Product

Resources

About