Journal of Cybersecurity and Information Management

Credit risk assessment along with delinquency management in banking receives substantial improvements from the introduction of Artificial Intelligence (AI) and behavioural insights. This research creates an extensive behavioural credit-scoring model through its discovery of crucial psychological characteristics including integrity and self-efficacy and locus of control and materialism that greatly affect credit default and wilful delinquency. A thorough evaluation of the predictive model occurs through logistic regression and confirmatory factor analysis (CFA) based analysis on 376 respondent data. Self-efficacy together with internal locus of control and materialism demonstrate significant power as predictors for credit risk and the willingness of individuals to default voluntarily is directly influenced by integrity and self-esteem. The ability of Artificial intelligence approaches to forecasting depends on behavioural constructs to optimize precision accuracy, reduce credit risk estimation errors, and provide opportunities for early prevention. The model delivers 92.1% accurate Default Risk classifications together with 91.0% precise predictions for Liquidity Risk while maintaining a Default Risk AUC-ROC measure of 0.96, which signifies its advanced predictive capabilities. The research demonstrates that artificial intelligence alongside behavioural credit scoring systems can enhance financial lending decisions while stabilizing credit markets.

The exponential growth of the Internet, distributed computing, and search engines has led to a steady improvement in the quality of Natural languge processing translation platforms that rely on these technologies. However, reusing the corpus is a challenge in the conventional translation setting. Other issues that translators frequently face include a tight cycle, challenging software manipulation, difficult internal and external cooperation, and inconsistent translation style. From this, the Natural languge processing Translation System (ETS) emerges incognito, with the primary goal of assisting all users in increasing translation efficiency and decreasing translation costs. This work uses research on Intelligent Big Data systems and Edge Computing to an Natural languge processing Translation System (BD-EC-ETS), which significantly advances the field of Natural languge processing translation with higher accuracy. With the Internet of Things and big data techniques, this article will examine a cutting-edge system for Natural languge processing translation software, identify its flaws and shortcomings, and provide data research to inform a system upgrade.The study focuses on Natural languge processing translation systemsto enhance the quality of the system's output translations. This paperexamines the current interactive language translation systems, focusing on those that use phrase models and get their information from edge computing enabled by the Internet of Things. Machine-efficient and cost-effective translation has emerged as a solution to such problems; researchers have focused on enhancing the Natural languge processing translation system's output quality via BD-EC-ETS. The system's outstanding performance in improving Natural languge processing translation accuracy and recall rate has been shown. Compared to the current Natural languge processing translation system, the accuracy improves by over 22% with fewer iterations and by as much as 100% with 80 iterations.

In biometric applications, deepfake detection is a major field of research, as it is vital to certify the authenticity and integrity of biometric data. The manipulation of biometric information, like facial and fingerprint images, presents a critical attack on patient confidentiality and healthcare security. Deepfake is one of the manipulated digital media, for instance, an image or video of an individual can be substituted with a resemblance of another being. On the other hand, the growth of deepfake technology sets major attacks on biometric security by making hyper-realistic fake individualities that can deploy authentication methods. For deepfake recognition, a vital method in biometric applications utilizes a machine learning (ML) system, mainly deep learning (DL) that might study to differentiate amongst real and fake biometric data. In this manuscript, we present a Design of an Artificial Intelligence-Based Biometric Authentication System for Deepfake Detection with Patient Data Privacy Protection and Identity Verification (AIBADD-PDPPIV) algorithm. The main intention of the AIBADD-PDPPIV model is to deliver a secure and efficient biometric authentication approach that contributes to the advancement of privacy-preserving biometric security in healthcare systems. To accomplish this, the AIBADD-PDPPIV method employs an image preprocessing stage using the adaptive median filter (AMF) to reduce noise and enhance essential biometric features. For feature extraction, the vision transformer (ViT) model can be employed to capture intricate spatial dependencies in biometric images. Moreover, the multi‐head attention mechanism-based bidirectional gated recurrent unit (MA-BiGRU) model is exploited for deepfake detection and authentication processes. Eventually, the hyperparameter tuning process is accomplished through the pelican optimization algorithm (POA) to improve the detection performance of the MA-BiGRU model. To show the improved performance of AIBADD-PDPPIV model, a wide sort of simulations take place and the outcomes are inspected under numerous measures. The comparison study reported the betterment of AIBADD-PDPPIV system under various metrics.

In the last few years, technology has developed so rapidly that many malware applications are available in the software market. Cybercrimes are increasing day by day with the usage of malware applications. Traditional approaches are not as effective in detecting malware. This study introduces a novel method for distinguishing malware from benign software applications using deep learning models like Denoising Autoencoder and Convolutional Neural Network. Initially, we extract binary code from the applications and transform it into grayscale images. Then, utilizing a denoising autoencoder, we improve the quality of the grayscale images by eliminating noise, and the Convolutional Neural Network uses processed images as input. Finally, the Convolutional Neural Network is employed to differentiate between malicious and benign applications. We test this methodology on the dataset that contains 10,810 malware and 1082 benign files. The suggested model obtains an accuracy of 97% and an F1-score of 96% and performs better than some traditional methods.

A resume is the first impression between you and a potential employer. Therefore, the importance of a resume can never be underestimated. Selecting the right candidates for a job within a company can be a daunting task for recruiters when they have to review hundreds of resumes. To reduce time and effort, we can use NLTK and Natural Language Processing (NLP) techniques to extract essential data from a resume. NLTK is a free, open source, community-driven project and the leading platform for building Python programs to work with human language data. To select the best resume according to the company’s requirements, an algorithm such as KNN is used. To be selected from hundreds of resumes, your resume must be one of the best. Therefore, our work also focuses on creating an automated system that can recommend the right skills and courses to help the desired candidates by using Natural Language Processing to analyze writing style (linguistic fingerprints) and also used to measure style and analyze word frequency from the submitted resume. Through semantic search and relying on individual resumes, forensic experts can query the huge semantic datasets provided to companies and institutions and facilitate the work of government forensics by obtaining official institutional databases. With global cybercrime and the increase in applicants seeking work and leveraging their multilingual data, Natural Language Processing (NLP) is making it easier. Through the important relationship between Natural Language Processing (NLP) and digital forensics, NLP techniques are increasingly being used to enhance investigations involving digital evidence and leverage the support of NLP for open-source data by analyzing massive amounts of public data.

Smile detection and recognition have been a key component of sentiment analysis, social robotics, human-computer interaction, and mental health monitoring before the advent of deep learning. Understanding and accurately identifying smiles can provide deep insights into human behavior, strengthen communication systems, and enhance adaptive responses in AI interfaces. This paper is a comprehensive review of algorithms developed for smile detection and recognition, and categorizes their main approaches into three traditional computer vision techniques: feature-based, machine learning-based, and deep learning-based. These techniques rely on handcrafted features such as edges, geometric features of the face, and texture, which give interpretability and limited adaptability. This paper explores feature extraction methods such as geometric and histogram-based features (e.g., histograms of directed gradients). In addition, this paper evaluates the effectiveness of traditional classifiers, including support vector machines that use machine learning-based methods, leveraging algorithms such as support vector machines (SVMs), extracted features to classify smiles with improved accuracy. Deep learning techniques, especially convolutional neural networks (CNNs) and hybrid methods provide end-to-end learning capabilities, extracting features directly from raw pixel data and enabling real-time performance. These frameworks, including recurrent neural networks (RNNs) for temporal analysis, generative adversarial networks (GANs) for data augmentation, and graph neural networks (GNNs) for structural analysis, have also pushed the boundaries of smile detection in dynamic and challenging environments. It also aims to provide a comprehensive overview of these classical methods, and analyze their strengths, limitations, drawbacks, and performance across diverse datasets of the proposed databases by focusing on describing these datasets and researchers’ methods of working on them as benchmarks for their research, and highlighting their importance in the environments and their contributions to the development of smile detection algorithms in the field of computer vision. Among these datasets are datasets such as CK+, FER2013, AffectNet, and Jaffe in developing, training, and evaluating smile detection and recognition algorithm models. By comparing these methodologies, our paper recommends directing future research towards more efficient, robust, and scalable solutions for smile detection and recognition in diverse applications.

As organizations increasingly rely on digital data, securing database systems has become a critical priority for protecting sensitive information, ensuring system integrity, and meeting regulatory compliance standards. This paper explores a comprehensive framework for database security, focusing on developing, assessing, and testing effective security tools. We begin by outlining the essential steps in creating robust security tools, including defining specific requirements based on database types and access needs and implementing real-time monitoring systems for immediate threat detection. The paper also emphasizes the importance of regular vulnerability assessments and advanced security analytics to identify and address potential risks proactively. Insights from a recent survey conducted among database administrators revealed that key areas of concern include access control, real-time monitoring, and vulnerability assessments. Furthermore, we highlight the significance of integrating security practices throughout the Software Development Life Cycle (SDLC). Additionally, best practices for evaluating and testing database security, including penetration testing to uncover vulnerabilities and stress testing to assess performance under load, are discussed. By synthesizing these strategies and survey feedback, this paper provides a comprehensive approach to enhancing database security, ensuring data protection, and maintaining system resilience against evolving cyber threats

Blockchain technology provides reliable data storage and secures transactions, however, is not suitable for devices with low resources because of its high computational and resource requirements. As quantum computing develops, it poses concerns regarding a cryptographic integrity of blockchain, making them more vulnerable to attacks. Blockchain technology is being used to enhance security and performance. The application of the post-quantum Ascon algorithm in a blockchain setting is presented in this paper. The Ascon hashing algorithm offers a lightweight, efficient architecture for resource-constrained applications, including mobile devices or Internet of Things-based blockchains. By providing high-speed hashing, authentication features, and defense against quantum attacks, it enhances performance and guarantees strong security without putting a strain on network infrastructure. The experimental results show using the Ascon algorithm in a blockchain environment is successful in reducing resource usage and execution time and significantly increasing randomness and unpredictability. Post-quantum Ascon algorithms overcome the drawbacks of traditional technologies and ensure that blockchain systems continue to withstand the new risks posed by quantum computing while increasing overall efficiency

While threats in cyberspace are in a state of constant evolution, the use of AI in cyber defense has numerous opportunities and dangers. This paper evaluates adversarial robustness for deep learning networks in network security applications by introducing a novel one-dimensional CNN model for malicious traffic detection. We conducted rigorous end-to-end processing and analysis of network traffic data, using a balanced dataset of 200,000 connections (46.52% benign, 53.48% malicious). Our model architecture includes three convolutional blocks (32, 64, and 128 filters, respectively) with batch normalization and dropout mechanisms (0.3 and 0.2, respectively). We use standardized feature scaling, label encoding for categorical features, and stratified sampling to maintain class distribution integrity.  Our proposed approach achieved remarkable performance metrics compared to standard approaches with a 95% AUC-ROC result (15% better than baseline CNN models) and detection rate of 99.99% malicious traffic (compared to 98.5% with standard architectures). The model demonstrates better robustness with only 10 false negatives out of 107,895 malicious samples, a 67% enhancement compared to current state-of-the-art systems. Training dynamics show great stability with minimal overfitting (validation/training loss difference of only 0.01), indicating good generalization ability.

As an increasing number of people and corporations move their data to the cloud side, how to ensure efficient and secure access to data stored on the cloud side has become a key focus of current research. Attribute-Based Encryption (ABE) is largely recognized as the best access control method for safeguarding the cloud storage environment, and numerous solutions based on ABE have been developed successively. Attribute-based encryption (ABE), which provides fine-grained access control and ensures data confidentiality, is widely used in data sharing. Hence, the strong and lightweight encryption schemes need more limelight of implementation in ABE to overcome the tampering and leakage problem that may cause the severe consequences to the users. To solve this problem, this paper proposes the Swarm Inspired Chaotic Encryption principles for designing the CP-ABE Systems for effective data sharing process. This scheme utilizes the chaotic properties along with the swarm properties for every individual transmission that leads to the strong defence characteristics. The intensive experimentation is carried out using Multi-modal Inputs such as the biometric images and eye iris images. The extensive experimentation is carried out using the various standard tests such as NIST (National Institute of Standard and technology), communication cost (CC) and metrics such as NPCR, UACI, entropies has been evaluated and analysed. Furthermore, excellence of the proposed model is determined by comparing with the other existing schemes. The evaluation demonstrates the CC of proposed scheme is only 30% than other algorithms and passed all the 12 standard tests. The experimental results illustrate the proposed scheme has more advantage in exhibiting the more randomness and light weight characteristics for health care which can more defensive against the attacks

We present a new metaheuristic optimization technique, the Dynamic Leader Sibha Algorithm (DLSA), based on the structured dynamics of the ‘Sibha’ (an Islamic tool). Using a hierarchical leader-follower framework, DLSA dynamically balances exploration and exploitation to resolve the difficulties of high dimensional and multimodal optimization. DLSA is applied to three well-known engineering problems, namely the Speed Reducer, Welded Beam, and Pressure Vesseldo, to tackle the objectives of minimizing the weight of these structures and achieving the desired results with regularity. Key results indicate that DLSA is faster in convergence, gives better quality solutions and is more robust among diverse problem domains. DLSA is an effective and reliable optimization tool that can readily be applied to solve real-world and complex engineering problems.

One of the most intriguing study subjects in the scientific world is medical data visualization. Researchers focus more on creating a medical that is reliable and efficient. Over the past ten years, varieties of methods have been developed, and investigation is still ongoing to improve healthcare systems' efficiency. To forecast or identify illnesses from medical information, the first stage in medical evaluation of information systems uses statistical techniques. However, statistical techniques yield unreliable findings due to the high amount and variety of the data, which affects the performance of the healthcare system. Numerous methods and solutions for conventional problems were made possible by the advancement of technology and the implementation of AI in the clinical field. To improve patient results and save medical expenses, acute illness prediction is essential. With an emphasis on diabetes, CVD, and specific cancers, this study investigates the effectiveness of many hybrid DL approaches in forecasting the beginning of chronic illnesses. Using a varied dataset of 100 thousand patient records, we evaluated the performance of a few hybrid methods, such as Autoencoder-Support Vector Machine (AE-SVM), Gradient Boosting-Neural Network (GB-NN), and Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM). Our findings show that when it came to forecasting the development of disease within a period of five years the CNN-LSTM model offered the greatest accuracy of 95.3%, closely followed by GB-NN with 94.1% and AE-SVM with 92.8%. Along with discussing the possible incorporation of these hybrid models into healthcare DSS, the study also found important predictive criteria. Our results indicate that hybrid DL techniques, as opposed to conventional single-algorithm approaches, can greatly improve early disease identification and treatment procedures in healthcare settings.

Biometric data is becoming increasingly valuable because of its uniqueness, and digital watermarking techniques are used to protect it. This paper presents a new method of hiding Palmprint images using wavelet decomposition and Encrypting Visual Information (EVI). EVI is a technique for securing Palmprint print images that has been extensively studied in this report. By embedding the Palmprint image in the cover image, and then using wavelet transformation, this output image can be decomposed into four segments (Segment Low Low, Segment Low High, Segment High Low, and Segment High High). A compressor is placed at the sender site to compress these four segments. DWT is obtained at the receiver side and then the bit-matching procedure is applied to obtain the original palmprint image. Using data concealing and EVI implementations on biometrics, palmprints, and related textual information can be protected from identity fraud. The watermarked cover images and palmprints, which could be used for authentication, have been improved from the existing approach. By reducing the segment size, quality is achieved along with higher security and bandwidth reduction. In addition, the three least significant bits are successfully applied to increase the length of a secret message while retaining palmprint quality.

The model mentioned in the study introduces a new Puzzle Optimization Algorithm-Based Fault Tolerant Scheduling (POAB-FTS) model specifically designed for the cloud computing setting. This pinpoints the significant challenge of achieving reliability, availability, and performance in resource scheduling in the context of failure cases, which is addressed by this novel technique. The POAB-FTS methodology integrates optimization using a game theory approach to perform actions that reduce execution time and failure probability while using a fitness function to provide better decision-making. This work entails an assessment of the main reasons behind task and hardware failures such as lack of resources, hardware defects, and suboptimal implementation. The model covers both active and passive fault tolerance approaches to workload balancing, migration before failure, and migration after failure points. Cooking schedules derived from the POAB-FTS technique are compared against the MAXMIN, ACO, and GTO-FTASS algorithms to present the makespan, failure ratios, and failure slowdowns—giving a comprehensive comparison of the method. As shown in this paper, the POAB-FTS framework can improve the system’s fault-tolerance and adapt resource allocation based on the actual demand thereby stressing its capacity to act as a scalable and cost-efficient solution for the improvement of cloud computing infrastructures. On this contribution, a sound and optimal cloud resource management is made possible.

This observe investigates the reasons and effects of cybersecurity way of life in IT agencies. Given the developing threats to cybersecurity and the essential role that organizational lifestyle plays in decreasing these risks, it's miles essential to realise the connection that exists among policy elements, employee conduct, and cyber security overall performance. By concentrating at the connections between distinct factors impacting cybersecurity culture and there have an effect on the efficacy of cyber security measures, the examine fills in gaps in empirical studies. This take a look act’s principal purpose is to behaviour an empirical investigation into the methods that many sides of cyber security culture, along with policy concerns, employee behaviour, and cyber security attention, have an effect on how properly cyber security measures work in IT companies. The studies in particular examines 3 hypotheses: (1) that coverage factors positively correlate with usual effectiveness; (2) that cyber security attention and engagement in preventive measures are predictively correlated; and (three) that behavioural worries are undoubtedly correlated with the implementation of powerful cyber security measures. Data had been collected the usage of a pass-sectional survey the use of a quantitative studies method. A stratified random pattern strategy became used inside the studies to select 100 IT employees from special corporations. A systematic questionnaire overlaying coverage variables, behavioural worries, cyber security recognition, preventative measures, and the perceived efficacy of cyber security strategies become used to collect information. The conclusions of the primary records had been in addition supported and given that means with the aid of secondary information taken from organizational reviews and already published literature. An enormous wonderful connection was discovered in the research between coverage variables and cyber security measures' efficacy, suggesting that robust regulations enhance cyber security overall performance as a whole. It has been proven that employee participation in preventative actions is extensively anticipated by cyber security recognition. The adoption of successful cyber security tactics turned into strongly correlated with behavioural issues. Aside from declaring regions where cyber security lifestyle needs to be stepped forward, the research additionally found gaps in preventative measures' efficacy. The study emphasizes how crucial it is to have clear policy guidelines and raise awareness of cyber security issues in order to encourage efficient cyber security practices in IT companies. The results provide insightful information on the dynamics of cyber security culture and offer doable recommendations for improving cyber security procedures and guidelines. Organizations may enhance their cyber security frameworks and strengthen their Defences against emerging threats by filling up the holes found in the report.