A creative approach to understanding the hidden information within the business data using Deep Learning

doi:10.1016/j.ipm.2021.102615

Information Processing & Management

Volume 58, Issue 5, September 2021, 102615

https://doi.org/10.1016/j.ipm.2021.102615 Get rights and content

Highlights

•
The Deep neural network-based invisible text steganalysis performs the fully specified extraction of both features and phrases related to the particular business to resolve such issues in business data sharing communication
•
A relative information entropy is obtained for a rough feature optimization. The feature matrices are recognized from the generated information entropy
•
From that matrix, the information in the particular matrix is weighted and based on the weights. The hidden business information is selected and extracted at the receiver end of the business transformation.

Abstract

Crucial business data is an essential asset for each business establishment. Data security is vital when sensitive data are transmitted over the Internet in a business environment. Steganography is the art of obscuring data inside a regular file of similar or different forms. For digital forensics, hiding data has always been necessary. The current information hiding method based on deep learning models can not directly use the original data as carriers, which means the method can not use the prevailing data in big data to hide information. Hence, this paper proposes a Deep neural network-based invisible text steganalysis (DNNITS) for business data hiding. This paper uses a word embedding layer to extract the syntax and semantic word features. A rough set of relative information entropy has been employed based on information features, and the optimized feature matrices are determined. The information in the optimized feature matrices are weighted, and the hiding information weighted feature is acquired. The findings reveal that our model can safely hide secret messages conveniently, quickly, and with no restriction on the business environment's data amount. The experimental results show that the suggested DNNITS model enhances the extraction rate of 95.4%, significance rate of 97.5%, the performance ratio of 89.6%, an efficiency ratio of 98.7%, recall ratio of 90.4%, and the lower error rate of 10.2% compared to other existing models.

Section snippets

Introduction to Text Steganalysis

The increasing demand for internet facilities in maintaining business records has explored security as a significant attention factor (Ahvanooey et al., 2020). Presently, text steganalysis has been extensively developed to perform the business world's hidden data processing, which enhances information security (Alazab et al., 2018). Text steganalysis is used to express the hidden information in the business data's actual messages (Manogaran et al., 2018). The embedment of such a process lies

Background Study

Taleby Ahvanooey et al. (Yang et al., 2020) aimed to discuss Web Text Security Analysis's reliability using Steganalysis (WTSAS). A study was conducted in small scale business industries. A possible improvement in results was obtained. Since the study sample is too small, the researchers cannot get a valid conclusion about the study.

Yang et al. (Singhal and Bedi, 2020) created a Prominent Steganalysis Hidden Information Sharing (PSHIS) based on several economic and business conditions. It is a

Deep neural network-based invisible text steganalysis (DNNITS)

In the modern business world, information is important in a secure and private organization to maintain confidentiality. Details should be available from the security perspectives when necessary. Attackers can alter the information resulting from the unavailability of information. From a security perspective, violators and encryption technology do not allow information readable and should convert the plain text to encoded text. Encryption technology is converting data into a hidden code that

Results and Discussion

As mentioned above, the proposed system has been executed in an effective online simulation business model. The method is compared with the system of security analysis and word text extraction analysis. Combinations of the semantic features and the syntactic meaning are used and compared with all approaches. For general extraction, the order of resemblance, illustration, and output in terms of execution period, comparisons are carried out. Besides, performance tests and measures for business

Conclusion

This study introduces a deep neural network-based invisible text steganalysis (DNNITS) for business data hiding and retrieval. The new system addresses the limitations of current programs. It is focused on word embedding to choose the best hidden texts using steganalysis. A syntactic and semantic structure is built by the text utilizing the information base, followed by the test in the business archive and the user's language. Assessment results reveal that the method introduced has performed

Author Statement

Conception and design of the study: Yuanfeng Luo acquisition of data: Yue Mo analysis and interpretation of data: Baoji Xie, Guijun Yang

Drafting the manuscript: Chuantao Yao

References (20)

M.T. Ahvanooey et al.
ANiTW: A novel intelligent text watermarking technique for forensic identification of spurious information on social media
Computers & Security
(2020)
A. Alazab et al.
Maximizing competitive advantage on E-business websites: A data mining approach
G. Manogaran et al.
In-Mapper combiner based MapReduce algorithm for processing of big climate data
Future Generation Computer Systems
(2018)
S. Namasudra et al.
Towards DNA based data security in the cloud computing environment
Computer Communications
(2020)
K. Sekaran et al.
Design of optimal search engine using text summarization through artificial intelligence techniques
Telkomnika
(2020)
G. Manogaran et al.
A Gaussian process based big data processing framework in cluster computing environment
Cluster Computing
(2018)
S. Kadry et al.
Massively Parallel Processing Distributed Database for Business Intelligence
Information Technology Journal
(2008)
M. Hussain et al.
Information hiding using edge boundaries of objects
International Journal of Security and its applications
(2011)
C. Qin et al.
Dictionary-based data hiding using image hashing strategy
Int J Innov Comput Inf Control: IJICIC
(2013)
C.C. Chang et al.
A steganographic scheme for reversible information hiding with good visual quality suitable for small embedded data

There are more references available in the full text version of this article.

Cited by (13)

Deep learning for steganalysis of diverse data types: A review of methods, taxonomy, challenges and future directions
2024, Neurocomputing
Steganography and steganalysis are two interrelated aspects of the field of information security. Steganography seeks to conceal communications, whereas steganalysis aims to discover or, if possible, recover the data they contain. These two areas have garnered significant interest, especially among law enforcement agencies. Cybercriminals and even terrorists often employ steganography to avoid detection while in possession of incriminating evidence, even when that evidence is encrypted, since cryptography is prohibited or restricted in many countries. Therefore, a deep understanding of cutting-edge techniques for uncovering concealed information is essential in exposing illegal activities. Over the last few years, a number of strong and reliable steganography and steganalysis techniques have been introduced in the literature. This review paper provides a comprehensive overview of deep learning-based steganalysis techniques used to detect hidden information within digital media. The paper covers all types of cover in steganalysis, including image, audio, and video, and discusses the most commonly used deep learning techniques. In addition, the paper explores the use of more advanced deep learning techniques, such as deep transfer learning (DTL) and deep reinforcement learning (DRL), to enhance the performance of steganalysis systems. The paper provides a systematic review of recent research in the field, including data sets and evaluation metrics used in recent studies. It also presents a detailed analysis of DTL-based steganalysis approaches and their performance on different data sets. The review concludes with a discussion on the current state of deep learning-based steganalysis, challenges, and future research directions.
CovertSYS: A systematic covert communication approach for providing secure end-to-end conversation via social networks
2022, Journal of Information Security and Applications
Citation Excerpt :
To encounter text steganography mechanisms, attackers design steganalysis models to identify whether a given CMH contains covert information and, if possible, eliminate or decode the embedded SM [12]. For example, Luo et al. [30] have proposed a deep learning-based text steganalysis model for extracting linguistic syntactic and semantic features from business data by focusing on the word-based feature extraction. Another text steganalysis method introduced by Yang et al. [31] predicts the correlations between words from stegotext by mapping each word to a semantic space.
While encryption can prevent unauthorized access to a secret message, it does not provide undetectability of covert communications over the public network. Implementing a highly latent data exchange, especially with low eavesdropping/discovery probability, is challenging for practical scenarios, such as social and political movements in authoritarian regimes, military operations, and privacy preservation. Moreover, the current literature suffers from a low embedding capacity and monolingual applicability, limiting the amount of hiding secret data within short text messages using state-of-the-art algorithms, e.g., linguistic-based, structural-based, or coverless-based solutions. In this paper, we present a systematic covert communication technique called CovertSYS that enables a multilingual secure end-to-end conversation via messaging or social network platforms. The CovertSYS functions by encrypting a confidential message using a multi-factor authentication scheme and converting the encoded binary data into hidden Unicode symbols to be transmitted under cover of short text messages. We then conduct extensive experiments to confirm the security and validity of the proposed technique against state-of-the-art approaches. Our experimental results show that the CovertSYS provides a superior mean performance of 91.53% by improving the criteria scores: embedding capacity rate of 100%, imperceptibility rate of 76.4%, and distortion robustness rate of 98.2%. Finally, we discuss the practical implications of the proposed technique compared to the existing text steganography methods.
Time-series classification with SAFE: Simple and fast segmented word embedding-based neural time series classifier
2022, Information Processing and Management
Citation Excerpt :
This embedding works better for natural language data sets with complex text structures, yet these approaches are also more expensive and heavy in design (Arora et al., 2020). Traditional word embedding models have been used in many contexts, including data classification tasks such as sentiment analysis (Behera, Jena, Rath, & Misra, 2021), Named Entity Recognition (Nozza, Manchanda, Fersini, Palmonari, & Messina, 2021) or topic analysis (Zhao et al., 2021) and other tasks such as business data parsing (Luo et al., 2021), reviews mining (Zhang, Fan, Zhang, Wang, & Fan, 2021) or fake news detection (Goldani, Safabakhsh, & Momtazi, 2021). This paper uses the word embedding technique in a new role: for time series classification.
Dictionary-based classifiers are an essential group of approaches in the field of time series classification. Their distinctive characteristic is that they transform time series into segments made of symbols (words) and then classify time series using these words. Dictionary-based approaches are suitable for datasets containing time series of unequal length. The prevalence of dictionary-based methods inspired the research in this paper. We propose a new dictionary-based classifier called SAFE. The new approach transforms the raw numeric data into a symbolic representation using the Simple Symbolic Aggregate approXimation (SAX) method. We then partition the symbolic time series into a sequence of words. Then we employ the word embedding neural model known in Natural Language Processing to train the classifying mechanism. The proposed scheme was applied to classify 30 benchmark datasets and compared with a range of state-of-the-art time series classifiers. The name SAFE comes from our observation that this method is safe to use. Empirical experiments have shown that SAFE gives excellent results: it is always in the top 5%–10% when we rank the classification accuracy of state-of-the-art algorithms for various datasets. Our method ranks third in the list of state-of-the-art dictionary-based approaches (after the WEASEL and BOSS methods).
The evaluation of enterprise supply chain intelligent manufacturing system for agricultural interconnection data based on machine learning
2024, Expert Systems
IASMFT: intelligent agent simulation model for future trading
2024, International Journal of Information Technology (Singapore)
A Review on the Recent Trends of Image Steganography for VANET Applications
2024, Computers, Materials and Continua

View all citing articles on Scopus

View full text

A creative approach to understanding the hidden information within the business data using Deep Learning

Highlights

Abstract

Section snippets

Introduction to Text Steganalysis

Background Study

Deep neural network-based invisible text steganalysis (DNNITS)

Results and Discussion

Conclusion

Author Statement

ANiTW: A novel intelligent text watermarking technique for forensic identification of spurious information on social media

Computers & Security

Maximizing competitive advantage on E-business websites: A data mining approach

In-Mapper combiner based MapReduce algorithm for processing of big climate data

Future Generation Computer Systems

Towards DNA based data security in the cloud computing environment

Computer Communications

Design of optimal search engine using text summarization through artificial intelligence techniques

Telkomnika

A Gaussian process based big data processing framework in cluster computing environment

Cluster Computing

Massively Parallel Processing Distributed Database for Business Intelligence

Information Technology Journal

Information hiding using edge boundaries of objects

International Journal of Security and its applications

Dictionary-based data hiding using image hashing strategy

Int J Innov Comput Inf Control: IJICIC

A steganographic scheme for reversible information hiding with good visual quality suitable for small embedded data