Journal of Cybersecurity and Information Management

This paper discusses about implementing Machine Learning Models with the Marine_Pulse dataset. This is about side-scan sonar images that have four groups: Engineering Platform (EP), Pipeline/Cable (P/C), Sea Bed Surface (SBS), and Underwater Residual Mound (URM). This manuscript performed some difficult feature extraction and classification methods using the DenseNet-DNN framework. This paper delves deeply into the implementation of the DenseNet121 Dropout, DenseNet201 Dropout, DenseNet201 Enhanced Dropout, and DenseNet201 Transfer Learning models. It investigates how these models perform on feature extraction and classification using a DNN. We enhanced the performance and reduced overfitting by applying a dropout to DenseNet121 and DenseNet201 and by adding transfer learning (TL) to DenseNet201, respectively. The models were evaluated based on the accuracy, precision, recall, F1-score, specificity, and classification errors of the training and testing samples. We observed that DenseNet201 Enhanced Dropout outperformed the other models, achieving the highest accuracy of 95.79%. DenseNet201 Dropout followed this achievement with an accuracy of 94.74% and DenseNet121 Dropout with an accuracy of 92.11%. DenseNet201 Transfer Learning, on the other hand, had the worst accuracy (92.11%).  Specificity is a measure of how well the model represents negative examples correctly. The maximum specificity was observed in DenseNet201 Enhanced Dropout (98.38%). DenseNet201 Dropout follows it at 97.96% and DenseNet121 Dropout at 97.18%. The smallest specificity was reported on DenseNet201 TL with 96.60%. This result demonstrates that our keys can generalize well and that they maintain high classification accuracy on the test data.

Traditional identity management systems are vulnerable to critical issues, such as privacy breaches and single points of failure, which compromise the security and integrity of user information. These centralized models require the disclosure of sensitive data to third parties, exposing users to heightened risks. To address these challenges and the emerging threat of quantum computing, this paper proposes a novel blockchain-based identity management architecture that employs blockchain’s decentralized, immutable ledger to eliminate centralized vulnerabilities, while zk-STARKs enable quantum-resistant, privacy-preserving identity verification without revealing sensitive information.The Framework integrate also InterPlanetary File System protocol for storing users data. This architecture establishes a user-centric, decentralized model that is resilient to both classical and quantum threats, and enhances privacy.

In India, vector-borne illnesses are becoming a bigger problem.  Because the government still faces difficulties in preventing and controlling these vector-borne illnesses, they have become a burden on society.  Every year, a sizable section of India's population contracts this illness.  Due to the difference in geographical and living standard of people, it becomes difficult to regulate these diseases at early stages in the present system. The main aim of the proposed research works was to design and developing a novel hybridized Kyasanur Forest Disease (KFD) prediction model that leverages a combination of rejuvenated machine-based learning model to enhancing seasonal forecasting & detection of vector-borne diseases. By integrating advanced algorithms such as SVM, NB, LR & Multi-layer perceptron, the research seeks to improving of the accuracy & reliabilities of the prediction related to KFD cases. This hybridized approach aims to better capture the complex relationships between seasonal factors, disease symptoms, and environmental conditions, thereby providing a more effective tool for early detection and management of KFD.

Certificate generation systems play an important role in higher education institutions because they prepare certified students for the job market and induce organizational efficiency. In this context, the College of Education for Pure Science / Ibn Al-Haitham (CEPSIH) does not, however, have its own electronic system. This point motivates us to conduct this monitoring situation as a case. We designed and implemented the Ibn al-Haitham Certificate System (IHCS) as an automated certificate generation database system at the CEPSIH. This case study aims to put this system in a real educational environment into a valuable context, where the successfully implemented system meets the objectives of CEPSIH, illustrates the major bottlenecks, the overwhelming challenges, and the negative impact resulting from a time-consuming, manual certificate issue process at the CEPSIH. The authorized staff members will generate certificates using IHCS database server with a user-friendly interface. Users (or the student graduators) will go through online panel and register before logging into the IHCS. Registered users authenticate themselves, after which new user accounts can be used to request the graduation certificate from IHCS database and then generated it automatically. To implement the IHCS, it was necessary to collect data from paper records and old Excel sheets which belong to more than 35000 graduates since 1980s. The collected data should be converted to CSV files which we designed in particular form in order to be imported to the IHCS database. Data verification and validation are conducted in specific manners within IHCS to ensure that all stored data are correct without any errors and meet certain standards of the CEPSIH. All graduate information stored in the IHCS database are encrypted by AIS algorithm using encryption key of 256 bit.

The integration of artificial intelligence (AI) and real-time information sharing is transforming the freight forwarding industry, enabling more sustainable and efficient green supply chains. However, the increasing reliance on interconnected systems raises significant cybersecurity challenges, particularly regarding secure data exchange and protection of sensitive information. This paper explores the critical role of cryptographic models and secure communication protocols in safeguarding real-time data sharing among AI-driven logistics networks. We analyze key security challenges faced by IoT-enabled freight systems and propose robust encryption and key distribution strategies to ensure confidentiality, integrity, and resilience. Our findings highlight the importance of secure information management in advancing sustainable, cyber-resilient supply chains that support environmental goals while maintaining operational efficiency.

Compressing color images (such as JPEG 2000) with wavelet transforms that are used in image parsing into approximate and detailed coefficients in the Multi Resolution Analyses (MRA) stage, such as Symlet 2, Coiflet 2, and Daubechies 2. The rapid development that occurs in modern life and the development of technology and artificial intelligence has increased the need to find an advanced and fast technology in image transfer, which requires reducing the space used by very large image data through the compression process that images need during transfer and transmission. Therefore, the need to accomplish this work has been necessitated by finding a new method and purely mathematical methods with equations and transformations that will be performed on Hermite polynomials to obtain the discrete Hermite wavelets (DHWT) to meet the great challenge in the field of images due to the mathematical properties that characterize these waves to be ready to perform the image analysis process known in the field of images (MRA), which is summarized in entering the color image to analyze the color image into two types of coefficients, which are detail coefficients and convergence coefficients due to the high level and low level, respectively, to divide the image into four blocks, which are Low Low, High Low, Low High and High High  to then remove the noise and then compress, A suitable algorithm was created in MATLAB to read the program for this tool as in common waves (Symlet 2, Coiflet 2, and Daubechies 2) to obtain good results with new wavelet. The results obtained and through comparisons with basic wavelet work such as Haar and Daubechies etc. to obtain the values of the most important image quality parameters and the experiment was carried out on a sample of JPEG 2000 The tables in this work show the results that will be obtained that prove the efficiency of the proposed model after calculating the image quality parameters Mean Square Error (MSE), Peak Signal of Noise Ratio (PSNR), Bit Per Pixel (BPP) and Compassion Ratio (CR). 

Security of digital communication becomes of prime importance due to the fast growing cybersecurity attacks. Classical encryption algorithms frequently drop down in offering the vital level of security required to safeguard critical information. The advances in cryptography methods are very important to solve this issue and ensure integrity and privacy.  This paper focuses on the weaknesses of the current methods through investigating mixing multiple encryption methods. The research explores whether combining Hash-based Message Authentication Code (HMAC), Elliptic Curve Cryptography (ECC), and Triple Data Encryption Standard (3DES) can provide upgrade to security for end-to-end encryption.  The chief objective is to improve and evaluate a powerful encryption framework that make use the strengths of HMAC, ECC and 3DES. This is done by showing how mixing these algorithms together can improve security and reliability levels to safeguard digital communications. An extensive analysis is performed by using several metrics. These involve ciphering and deciphering speed, key generation, NIST test and Avalanche effect. The results show that these combinations increase significantly security level of digital communication. It shows better performance than traditional cryptography in both security and speed. Combining HMAC, ECC and 3DES provide practical solution to increase security level in end-to- end encryption. It improves the vulnerabilities in traditional cryptography by building multi-layer security framework. It is concluded that the proposed framework is powerful and a candidate for developing and has strong resistance against cyber threats.

In an era where digital technologies dominate all aspects of life, image encryption has emerged as a fundamental pillar of data protection and securing sensitive information. With the rise of sophisticated cyber threats and attacks, the search for innovative and stronger encryption methods has become an urgent necessity. This research proposes an enhanced image encryption scheme combining the Arnold map, 2D Henon map, memristor elements, and exponential nonlinearity chaos techniques to address vulnerabilities in conventional encryption methods. The hybrid approach ensures robustness against statistical, differential, and brute-force attacks. Experimental results demonstrate superior performance with unified histogram distribution, including near-ideal information entropy (7.99941), infinite peak signal-to-noise ratio (PSNR), and high resistance to differential attacks (NPCR = 99.61%, UACI = 35.08%). A keyspace of  and key sensitivity correlation difference rate (CDR) of 99.61% further validate security. Comparative analysis with recent studies confirms the proposed method’s superiority in encryption strength and computational performance. Consequently, the results of the proposed method making it a promising option for high-security image protection applications.

Cloud-based Enterprise Resource Planning (ERP) systems have become essential to organizational operations in today's digital environment, acting as the cornerstone for managing sensitive corporate data. ERP system integration with third-party apps, however, poses serious security risks because businesses cannot afford data breaches or illegal access that could jeopardize financial records, operational integrity, and reputation. Because ERP systems are appealing targets for cybercriminals looking to obtain sensitive company data, ensuring secure data exchange is an urgent concern. ERP integration security is still a problem, despite the numerous security frameworks and measures that have been put forth. Current methods frequently fall short of effectively addressing new threats. To guarantee the safe and smooth integration of cloud-based ERP solutions with external systems, this study presents an extensible security framework. The framework reduces the risk of data interception and unauthorized access by utilizing functional and technical security measures to produce a strong, adaptable security model. To prevent data leaks and unauthorized changes, the implementation is divided into two phases: (1) securing outbound data flow from the ERP portal to third-party systems, and (2) securing inbound data flow from third-party systems into the ERP portal, which protects against malicious intrusions and breaches of data integrity.

Multi-cloud computing is emerging as a transformative solution to meet the extensive computational demands of Internet of Things (IoT) devices. In networks with multiple devices and clouds, factors such as real-time computing requirements, fluctuating wireless channel conditions, and dynamic network scales introduce significant complexity. Addressing these challenges, along with the resource constraints of IoT devices, is essential for effective multi-cloud integration.  This paper proposes a hybrid decision-offloading model that integrates continuous and discrete decision-making. IoT devices must learn to make coordinated decisions regarding cloud server selection, task offloading ratios, and local computation capacity. This dual-layer decision-making process involves managing both continuous and discrete variables, along with inter-device coordination, which poses considerable challenges. To address these, we introduce a probabilistic approach that transforms discrete actions, such as selecting a cloud server, into a continuous domain. We further develop a Privacy-Aware Multi-Agent Deep Reinforcement Learning (PA-MADRL) framework that combines centralized training with distributed execution. This framework minimizes overall system costs by considering energy consumption and cloud server rental fees. Each IoT device operates as an agent, autonomously learning efficient policies while alleviating its computational burden.  Experimental results demonstrate that the PA-MADRL framework effectively adapts to dynamic network conditions, learning optimal offloading policies. It significantly outperforms four state-of-the-art deep reinforcement-learning models and two heuristic methods, achieving lower system costs and improved resource efficiency.

In recent years, federated learning (FL) has emerged as a decentralized approach to model training, enhancing data privacy by retaining data on local edge devices. While existing privacy-preserving FL frameworks, like Secure Aggregation and Homomorphic Encryption, protect data through encrypted aggregation, they often face challenges with high communication overhead, significant computational demands, and increased energy consumption. Differential privacy approaches, though customizable via privacy budgets, may also degrade model accuracy due to added noise. Addressing these limitations, we propose PrivaNet-FL (Privacy-Optimized Network for Federated Learning), an advanced FL model that optimizes privacy techniques with minimal energy costs in edge environments. PrivaNet-FL incorporates adaptive privacy and efficiency management across edge devices, such as IoT sensors and smartphones, where data processing and real-time privacy adjustments conserve energy while maintaining data security. The framework consists of three main workflows: (1) Adaptive Privacy-Scaling-modulating privacy based on device constraints, ensuring optimal energy usage through dynamic adjustments of noise in differential privacy or encryption complexity; (2) Lightweight Encryption and Secure Aggregation-employing low-complexity encryption and secure aggregation techniques, such as random masking and distributed averaging, to minimize energy without compromising data privacy; and (3) Energy-Aware Communication-Efficient FL-leveraging model compression, energy-aware scheduling, and differential privacy with controlled noise to reduce communication and energy overhead. Results demonstrate that PrivaNet-FL achieves superior model accuracy with reduced energy and communication costs compared to traditional FL methods, making it ideal for privacy-sensitive and resource-limited edge applications.

Network security faces significant challenges due to the increasing sophistication of cyber threats and the inherent class imbalance in intrusion detection datasets. To address this issue, a hybrid Boundary Equilibrium Generative Adversarial Network (BEGFAN) and Vector Quantization Variational Autoencoder (VQVAE) framework, termed BVQVAE, is proposed for Network Intrusion Detection Systems (NIDS). The framework involves preprocessing, feature extraction, and class balancing to enhance classification accuracy. Missing values are imputed, categorical features are label-encoded, and numerical attributes are normalized to ensure a structured dataset. BEGAN generates synthetic samples to mitigate class imbalance, while VQVAE extracts essential features using an encoder with quantization and a decoder for network traffic reconstruction. The model is evaluated on NSL-KDD and UNSW-NB15 datasets, achieving 82.56% accuracy, with precision, recall, G-mean, and F1-score of 86.53%, 87.65%, 86.21%, and 87.08%, respectively.

Medical image analysis plays a vital role in diagnosis of diseases and the need of the day is to arrive at a simple and efficient compression technique. This paper proposes a comparative analysis of three different wavelet based medical image compression techniques. First algorithm is based on Bi-orthogonal wavelet with Parallel coding  (BiWT-PC) , second is based on Haar wavelet with block coding  (HWT-BC) and third algorithm is based on stationary wavelet transform with Parallel coding (SWT-PC). In this work, 3D medical image is converted into 2D slices and preprocessed using lifting scheme. Wavelet transform is applied to this preprocessed image, which divides the image into multilevel sub-bands. Then, the suitable encoding method is applied to get the compressed image. At the receiver side, the original image is recovered back by applying inverse wavelet transform and proper decoding over the compressed image. Experimentations are carried out over MRI and CT images with four quantitative metrics such as PSNR, CR, DcT and EcT. From the experimental analysis, it is observed that SWT-PC method is quite efficient since it has high PSNR and low CR.