Arabic Text Steganography Based on Deep Learning Methods

Adeeb, Omer Farooq Ahmed; Kabudian, Seyed Jahanshah

doi:10.1109/access.2022.3201019

Cited by 16 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, NMT has demonstrated outstanding performance in various machine translation tasks such as English-German and English-French translations [ 29 , 30 ]. Unlike SMT, NMT consists of an Encoder-Decoder architecture.…”

Section: Methodsmentioning

confidence: 99%

A novel method for linguistic steganography by English translation using attention mechanism and probability distribution theory

Lin,

Wang

2024

PLoS ONE

View full text Add to dashboard Cite

To enhance our ability to model long-range semantical dependencies, we introduce a novel approach for linguistic steganography through English translation. This method leverages attention mechanisms and probability distribution theory, known as NMT-stega (Neural Machine Translation-steganography). Specifically, to optimize translation accuracy and make full use of valuable source text information, we employ an attention-based NMT model as our translation technique. To address potential issues related to the degradation of text quality due to secret information embedding, we have devised a dynamic word pick policy based on probability variance. This policy adaptively constructs an alternative set and dynamically adjusts embedding capacity at each time step, guided by variance thresholds. Additionally, we have incorporated prior knowledge into the model by introducing a hyper-parameter that balances the contributions of the source and target text when predicting the embedded words. Extensive ablation experiments and comparative analyses, conducted on a large-scale Chinese-English corpus, validate the effectiveness of the proposed method across several critical aspects, including embedding rate, text quality, anti-steganography, and semantical distance. Notably, our numerical results demonstrate that the NMT-stega method outperforms alternative approaches in anti-steganography tasks, achieving the highest scores in two steganalysis models, NFZ-WDA (with score of 53) and LS-CNN (with score of 56.4). This underscores the superiority of NMT-stega in the anti-steganography attack task. Furthermore, even when generating longer sentences, with average lengths reaching 47 words, our method maintains strong semantical relationships, as evidenced by a semantic distance of 87.916. Moreover, we evaluate the proposed method using two metrics, Bilingual Evaluation Understudy and Perplexity, and achieve impressive scores of 42.103 and 23.592, respectively, highlighting its exceptional performance in the machine translation task.

show abstract

Section: Methodsmentioning

confidence: 99%

A novel method for linguistic steganography by English translation using attention mechanism and probability distribution theory

Lin,

Wang

2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…This technique modifies the cover text following the cover text language rule without changing its original meaning [11,12]. A machine learning-based algorithm may also be implemented to achieve a natural watermarked text [13].…”

Section: A Text Watermarking Schemementioning

confidence: 99%

“…This technique is robust against watermarking schema attacks such as OCR and retyping. However, since the linguistic-based technique modifies the content of the original cover text, this technique is unusable for a sensitive document that cannot be tempered [11,12,13]. Moreover, a high computational cost in a machine learning-based algorithm is not applicable in a low computational environment such as social media.…”

Section: A Text Watermarking Schemementioning

confidence: 99%

Improving ANiTW Performance Using Bigrams Character Encoding and Identity-Based Signature

Rofiatunnajah

Barmawi

2023

IEEE Access

View full text Add to dashboard Cite

Several threats, such as misinformation and hoax, exist in social media as a frequently used technology to exchange information. These threats can be prevented if the reader can verify the message's content integrity and source authenticity. One recent solution to overcome these threats was proposed by Ahvanooey et al. called ANiTW. ANiTW uses an invisible text watermarking scheme to verify social media message integrity and identify the message source. However, ANiTW is still vulnerable to undetected malicious text modification. Moreover, ANiTW has no tools to authenticate the extracted message source. The proposed method aims to overcome those vulnerabilities and improve ANiTW performance as a tool to verify message content integrity and message source authenticity in social media. To overcome vulnerabilities in ANITW, a part of the message hash and IBS-based signature is introduced as the watermark. The message integrity is verifiable by using part of the message hash as a watermark to detect any malicious. Moreover, implementing an IBS-based signature enables any reader to verify the message source's authenticity easily. In addition, to improve ANITW performance in embedding capacity and invisibility, a novel bigram-based character encoding and embedding rule are also introduced. Based on the experiment and analysis result, it is proven that the proposed method can perform better than ANiTW in the security, embedding capacity, and invisibility aspects.

show abstract

“…However, the challenges faced by non-native speakers in learning Arabic must be addressed. In addition to understanding grammar and vocabulary, speaking skills with fluency and familiarity with accent and intonation become crucial elements (Adeeb et al, 2022;Almurayh, n.d.;Alsadoon, 2021;Mohammed & Abdullah, 2022). In response to these complexities, Artificial Intelligence (AI) emerges as a promising alternative to enhance the quality of Arabic language learning.…”

Section: Introductionmentioning

confidence: 99%

Development of AI-based Arabic Learning Model to Improve non-native speaker Arabic Speaking Skills

Syaikhudin,

Laili

2024

Syaikhuna

View full text Add to dashboard Cite

This research delves into the development of an Artificial Intelligence (AI)-based Arabic language learning model with the aim of enhancing Arabic speaking skills for non-native speakers. The background of this research arises from the complexity of Arabic language learning, which requires not only an understanding of grammar and vocabulary but also proficiency in speaking with an accurate accent and intonation. The research methodology includes the selection of suitable AI algorithms, the development of a prototype model, and further testing on non-native speakers at the Sekolah Tinggi Agama Islam (STAI) al-Yasini, Pasuruan. The utilization of AI technology is expected to provide innovative solutions to address individual learning needs in the context of the Arabic language. Mid-term evaluation results indicate that the AI learning model can positively impact Arabic speaking skills, although some improvements are still necessary. User response analysis provides valuable insights that serve as the basis for further model refinements. Suggestions for future research include further development of the AI model, broader testing across various non-native speaker groups, and the integration of user feedback to enhance Arabic speaking skills holistically. The implications of these research findings are expected to make a significant contribution to the development of adaptive and innovative Arabic language learning.

show abstract

Arabic Text Steganography Based on Deep Learning Methods

Cited by 16 publications

References 27 publications

A novel method for linguistic steganography by English translation using attention mechanism and probability distribution theory

A novel method for linguistic steganography by English translation using attention mechanism and probability distribution theory

Improving ANiTW Performance Using Bigrams Character Encoding and Identity-Based Signature

Development of AI-based Arabic Learning Model to Improve non-native speaker Arabic Speaking Skills

Contact Info

Product

Resources

About