Enhanced Visual Cryptographic Schemes with Essential Access Structures and Pixel-Wise Operations

M.; Devi; R.; R.; S.

doi:https://doi.org/10.54216/JCIM.140221

Neutrosophic and Information Fusion | 2024

On The Algebraic Properties of 3-Cyclic Refined Neutrosophic Matrices with Real Entries

The objective of this paper is to study some of the elementary algebraic properties of 3-cyclic refined neutrosophic matrices with real entries, where we study the algebraic structure of the multiplication operation and its properties such as associativity, commutativity, and the existence of algebraic multiplication inverse. Also, we illustrate many examples that explain the validity of our work.

groups

Noor Edin Rabeh mail

link https://doi.org/10.54216/NIF.030101

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Neutrosophic and Information Fusion | 2024

On The Algebraic Properties of the Multiplication Operation of 4-Cyclic Refined Neutrosophic Real Matrices

The objective of this paper is to study some of the elementary algebraic properties of 4-cyclic refined neutrosophic matrices with real entries, where we study the algebraic structure of the multiplication operation and its properties such as associativity, commutativity, and the existence of algebraic multiplication inverse. Also, we illustrate many examples that explain the validity of our work.

groups

Noor Edin Rabeh mail

link https://doi.org/10.54216/NIF.030102

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Neutrosophic and Information Fusion | 2024

On The Analysis of Some Deep Learning Algorithms for Object Detection and Applications

The traditional methods of discovering objects no longer meet the requirements of the times as a result of their reliance on non-dynamic methods and as a result of their slow performance in light of the world's dependence on a huge amount of multimedia and social media. With the rapid development of deep learning providing more powerful tools capable of manipulating high-level and complex semantic features of objects. Several techniques have been developed to detect objects using deep learning algorithms. This research presents a comparative analysis of the most famous deep learning techniques for object detection, explaining their mechanisms, use cases and an experimental evaluation of their performance.

groups

Sandy Montajab Hazzouri mail

link https://doi.org/10.54216/NIF.030103

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Neutrosophic and Information Fusion | 2024

On The Problem of the Estimation of Variance Components Based On Non-linear Maximization Approach

In this paper, we study the problem of estimating variance components in the two-way classification with interaction in the random effect linear model by non-linear maximization. We assume the model according to the assumptions and give the theory of derivation of the estimators of these components, then apply these estimators on real data and obtain the estimates. We estimate these components by two other methods: the solution of the expected equation of mean square in the analysis of the variance table, and the minimum variance quadratic unbiased estimator.

groups

Ahmad Khaldi mail

link https://doi.org/10.54216/NIF.030104

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Neutrosophic and Information Fusion | 2024

On The Bayesian Estimation of Parameters of SQDM

This work is concerned with the problem of estimating parameters of spatial quadratic models by Bayesian technique (SQDM). This technique involves the prior information of the first and second moment of the parameters, where its estimation model is called the Bayesian quadratic unbiased estimator. The results of the estimation are taken in compared with the estimates of minimum norm quadratic unbiased estimators.

groups

Murtada Ali Maqdisi mail

link https://doi.org/10.54216/NIF.030105

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2024

A Hybrid Genetic Algorithm and Neural Network-Based Cyber Security Approach for Enhanced Detection of DDoS and Malware Attacks in Wide Area Networks

This study addresses the growing threat of network attacks by exploring their types and analyzing the challenges associated with their precise detection. To mitigate these threats, we propose a novel cyber security approach that integrates Genetic Algorithm (GA) and neural network architecture. The GA is employed for the selection and optimization of attributes that represent DDoS and malware attack features. These optimized features are then fed into a neural network for training and classification. The effectiveness of the proposed approach was evaluated through precision, recall, and F-measure analyses, demonstrating superior detection capabilities for DDoS and malware attacks compared to existing methods. Furthermore, we introduce a hybrid approach that combines Swarm Intelligence (SI) and nature-inspired techniques. The GA is utilized to select features and reduce the dataset size, followed by the application of Discrete Wavelet Transform (DWT) with Artificial Bee Colony (ABC) to further filter irrelevant features. The results show that this hybrid approach significantly enhances the accuracy and efficiency of network attack detection in wide area networks.

groups

Anusooya .S mail -

N. Revathi mail -

Sivakamasundari .P mail -

A. N. Duraivel mail -

S. Prabu mail

link https://doi.org/10.54216/JCIM.140217

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2024

Multi-Fusion Biometric Authentication using Minutiae-Driven Fixed-Size Template Matching (MFTM)

In today's digital era, ensuring robust and secure authentication mechanisms is crucial. Multi-fusion biometric authentication systems have emerged as a powerful solution to enhance security and reliability by integrating multiple biometric traits. This paper presents a novel Multi-Fusion Biometric Authentication approach using Minutiae-Driven Fixed-Size Template Matching (MFTM). The proposed method leverages the unique features of minutiae points in fingerprints and combines them with other biometric modalities, such as iris and facial recognition, to create a fixed-size template for matching. The fusion process involves extracting and normalizing minutiae points from the fingerprint, followed by their integration with iris and facial features using a robust feature fusion algorithm. The fixed-size template ensures consistency and efficiency in the matching process, addressing challenges related to template size variability and computational overhead. Extensive experiments conducted on standard biometric datasets demonstrate that the proposed MFTM approach significantly enhances authentication accuracy, reduces false acceptance and rejection rates, and provides a highly secure and scalable authentication solution suitable for various applications, including access control and identity verification. The results show an authentication accuracy of 98.7%, a false acceptance rate (FAR) of 0.2%, and a false rejection rate (FRR) of 0.5%. Additionally, the computational time for matching is reduced by 25% compared to traditional methods, highlighting the efficiency and practicality of the proposed approach.

groups

B. R. Sathishkumar mail -

K. M. Monica mail -

D. Sasikala mail -

M. N. Sudha mail

link https://doi.org/10.54216/JCIM.140218

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2024

Detect and Prevent Attacks of Intrusion in IOT Devices using Game Theory with Ant Colony Optimization (ACO)

A more extensive attack surface for cyber incursions has resulted from the fast expansion of Internet of Things (IoT) devices, calling for more stringent security protocols. This research introduces a new method for protecting Internet of Things (IoT) networks against intrusion assaults by combining Game Theory with Ant Colony Optimization (ACO). Various cyber dangers are becoming more common as a result of the networked nature and frequently inadequate security measures of IoT devices. Because these threats are ever-changing and intricate, traditional security measures can't keep up. An effective optimization method for allocating resources and pathfinding is provided by ACO, which takes its cues from the foraging behavior of ants, while Game Theory provides a strategic framework for modeling the interactions between attackers and defenders. Attackers and defenders in the proposed system are modeled as players in a game where the objective is to maximize their payout. Minimizing damage by anticipating and minimizing assaults is the defender's task. The monitoring pathways are optimized and resources are allocated effectively with the help of ACO. In response to changes in network conditions, the system dynamically modifies defensive tactics by updating the game model in real time. The results of the simulation show that the suggested method successfully increases the security of the Internet of Things. Compared to 87.4% using conventional approaches, the detection accuracy increased to 95.8%. From 10.5 seconds down to 7.3 seconds, the average reaction time to identified incursions was cut in half. Furthermore, there was a 20% improvement in resource utilization efficiency, guaranteeing that defensive and monitoring resources were allocated optimally. Internet of Things (IoT) network security is greatly improved by combining Game Theory with Ant Colony Optimization. In addition to enhancing detection accuracy and reaction times, this combination method guarantees resource efficiency. The results demonstrate the practicality of this approach, which offers a solid foundation for protecting Internet of Things devices from ever-changing cyber dangers.

groups

S. Aruna mail -

Kalaivani .N mail -

Mohammedkasim .M mail -

D. Prabha Devi mail -

E. Babu Thirumangaialwar mail

link https://doi.org/10.54216/JCIM.140219

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2024

Development of a Cryptographic Model Using Digits Classification for Cyber Security Applications

In the digital age, the safeguarding of information through effective cybersecurity measures is paramount. This paper presents the development of a robust cryptographic model tailored for cybersecurity applications. The background underscores the increasing prevalence of cyber threats and the necessity for advanced encryption techniques to ensure data confidentiality, integrity, and authenticity. The methodology involves the design and implementation of the cryptographic model using state-of-the-art algorithms and protocols. Rigorous testing and evaluation were conducted to assess the model's performance in various cyber environments. The results indicate that the proposed model significantly enhances security, demonstrating high resistance to common cyber-attacks with an average encryption time of 0.5 seconds for a 1MB file and a decryption accuracy rate of 99.9%. The model also achieved a data integrity verification success rate of 99.8% and an overall system efficiency improvement of 45% compared to existing models. The conclusion highlights the model's effectiveness and potential for broad application in securing digital communication, offering a substantial contribution to the field of cybersecurity.

groups

K. Jayakumar mail -

K. Sivakami mail -

P. Logamurthy mail -

P. Sathiyamurthi mail -

N. Chandrasekaran mail

link https://doi.org/10.54216/JCIM.140220

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2024

Enhanced Visual Cryptographic Schemes with Essential Access Structures and Pixel-Wise Operations

By splitting a picture into many parts, which, when reassembled, disclose the original image without requiring complicated math, visual cryptography is a strong method for protecting visual information. Problems with pixel enlargement, decreased picture quality, and restricted access structures are common with traditional visual cryptography techniques. Our proposed improved visual cryptography approach incorporates pixel-wise operations and critical access structures to solve these challenges and increase flexibility, picture quality, and security. To reconstruct a picture, our technique calls for building visual cryptographic shares based on critical access structures that specify the exact combinations of shares needed. In order to maintain the image's resolution and reduce pixel expansion, we use pixel-wise processes. By improving the peak signal-to-noise ratio (PSNR) by up to 20% compared to conventional approaches, experimental data show that our strategy greatly improves picture quality. In addition, the suggested approach guarantees that individual shares do not disclose any information on the original picture, thereby maintaining high security requirements. Finally, it is clear that the enhanced visual cryptographic system is well-suited for a wide range of uses in safe communications and data security due to its strong solution for secure picture sharing, increased picture quality, and adjustable access control.

groups

M. Revathi mail -

Devi .D mail -

R. Menaha mail -

R. Dineshkumar mail -

S. Mohan mail

link https://doi.org/10.54216/JCIM.140221

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new