Journal of Cybersecurity and Information Management

Journal DOI

https://doi.org/10.54216/JCIM

Submit Your Paper

2690-6775ISSN (Online) 2769-7851ISSN (Print)

Effective Integration of Database Security Tools into SDLC Phases: A Structured Framework

Ahmed Naguib , Haba K. Aslan , Khaled M. Fouad

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

Read More

Doi: https://doi.org/10.54216/JCIM.160114

Vol. 16 Issue. 1 PP. 176-207, (2025)

AI-Driven Features for Intrusion Detection and Prevention Using Random Forest

Mohammed B. Al-Doori , Khattab M. Ali Alheeti

In this research, we investigate sophisticated methods for Intrusion Detection Systems (IDS) and Intrusion Prevention Systems (IPS), leveraging AI-based feature optimization and diverse machine learning strategies to bolster network intrusion detection and prevention. The study primarily utilizes the NSL-KDD dataset, an enhanced version of the KDD Cup 1999 dataset, chosen for its realistic portrayal of various attack types and for addressing the shortcomings of the original dataset. The methodology includes AI-based feature optimization using Particle Swarm Optimization and Genetic Algorithm, focusing on maximizing information gain and entropy. This is integrated with the use of Random Forest (RF) to reduce class overlapping, further enhanced by boosting techniques. Grey Wolves Optimization (GWO) alongside Random Forest. This innovative approach, inspired by grey wolf hunting strategies, is employed for classification tasks on the NSL-KDD dataset. The performance metrics for each intrusion class are meticulously evaluated, revealing that the GWO-RF combination achieves an accuracy of 0.94, precision of 0.95, recall of 0.93, and an F1 score of 0.94.

Read More

Doi: https://doi.org/10.54216/JCIM.160101

Vol. 16 Issue. 1 PP. 01-14, (2025)

Critical Feature Selection Technique for Improving Performance Classification Model in Adaptive Intrusion Detection System

Anggit Ferdita Nugraha , Yoga Pristyanto , Beti Wulansari , Dian Prasetya

A firewall is one of the devices that supports network security, especially at the organizational level. A Firewall's effectiveness in supporting network security is highly dependent on the capabilities and abilities of the Network Administrator. Unfortunately, the high complexity of creating rules and the process of configuring Firewall rules carried out statically by the Network Administrator weakens the effectiveness of the Firewall, and it cannot adapt to increasingly dynamic network pattern changes. Machine Learning is one of the potentials that can be used so that the Firewall can work adaptively. Adaptive Firewall configuration in recognizing various attacks in the network will undoubtedly increase the effectiveness of the Firewall in ensuring network security. The success of the machine learning model performance cannot be separated from the dataset used during the learning process. The dataset used in learning often has a large dimension, but various noises and attributes are irrelevant in representing one class of data. Therefore, it is necessary to support the feature selection technique, which will show the presence of relevant characteristics in the dataset and maximize the machine learning model's performance. This study will be conducted on adding feature selection techniques to develop machine learning models on the Benchmark dataset related to network security. Various popular feature selection techniques will be evaluated, and their performance will be compared based on scenarios between feature selection techniques or scenarios that only use a single classification.

Read More

Doi: https://doi.org/10.54216/JCIM.160102

Vol. 16 Issue. 1 PP. 15-24, (2025)

Efficient Algorithms for Fuzzy Centrality Measures in Large-Scale Social Networks

Songa Venkata Rao , Bodapati Prajna

Numerous criteria are in place for social network applications. They require identification of network's core nodes. Traditional centrality measurements focus on specific node's direct connections or reachability. Often this disregards inherent ambiguity and complexity in real-world social networks. To address these constraints, we have introduced new method called Node Pack Fuzzy Information Centrality based on Pythagorean Neutrosophic Fuzzy Theory. Three essential values truth, falsity and indeterminacy have been added to this approach. This new approach provides a thorough depiction of social networks and it also offers a more sophisticated comprehension of connections between nodes. Complex and ambiguous interactions between entities can be effectively expressed using Pythagorean Neutrosophic values. Unlike traditional values, Pythagorean Neutrosophic values consider several uncertainty dimensions; this is a major improvement over traditional fuzzy value. Our approach handles relational complexity well and it includes self-weight for every node too. It represents each node's unique value, significance, or impact on the network. The network assessment is now more precise and contextual so we can assess centrality with greater precision. We applied this approach to a small academic network called university faculty/researchers. The application of Node Pack Fuzzy Information Centrality yielded promising results. It can enhance various activities associated with social network analysis. It can also offer valuable insights into the network architecture.

Read More

Doi: https://doi.org/10.54216/JCIM.160103

Vol. 16 Issue. 1 PP. 25-37, (2025)

A Constraint Satisfaction Approach for Estimating the RSA Prime Factors towards Known Bits Factorization Attacks

Daniel Asiedu , Patrick Kwabena Mensah , Peter Appiahene , Peter Nimbe

The Rivest–Shamir–Adleman (RSA) cryptosystem is one of the most prevalently utilized public-key cryptographic systems in current practice. Prior investigations into vulnerabilities of this cryptosystem have concentrated on diminishing the complexity associated with the integer factorization challenge, which is integral to the RSA modulus, expressed as 𝑁=𝑝𝑞. Possessing partial knowledge about the least significant digits (LSDs) of both p and q is a common assumption attacker’s advantage to enable the polynomial-time factorization of N, ultimately undermining the security of RSA. This paper presents a novel heuristic algorithm predicated on the Constraint Satisfaction Problem (CSP) principles, which estimates k-LSD pairs of the RSA prime factors,  and . The proposed Generate and Test (GT) and Backtracking with Heuristic Variable Ordering (BHVO) solver guarantees polynomial-time factorization of known bits by iteratively refining candidate pairs and eliminating invalid combinations through effective constraint propagation. The proposed approach obviates the requirement for specialized hardware for side-channel attacks to reveal a portion of  and . In our results, we have successfully estimated up to 5-LSDs of  and  with a reduced number of iterations and factored 2048 bits, N based on the known 4-LSDs of the prime in polynomial time. Our research lays the groundwork for factorization algorithms that require partial knowledge of the prime factors. We have highlighted the possible vulnerabilities linked to existing RSA key generation techniques. These may make RSA moduli susceptible to the attacks discussed in this study and proposed countermeasures to ensure secure prime generation.

Read More

Doi: https://doi.org/10.54216/JCIM.160104

Vol. 16 Issue. 1 PP. 38-52, (2025)

Implementing Comparative Analysis on Feature Engineering Techniques and Multi-Model Evaluation Framework for IDS

Neha Sharma , Abhishek Kajal

In recent years, most of the current intrusion detection methods run for critical information infrastructure are tested for IDS datasets, but does not provide desired protection against emerging cyber- threats. Most machine and deep learning-based intrusion detection methods are inefficient on networks due to their high imbalanced or noisy IDS datasets. Therefore, in this paper, our proposed work implements a comprehensive framework, using multiple models of machine learning and deep learning by taking advantage of advanced feature engineering approaches. Our research explores the impacts of a variety of feature engineering approaches on dimensionality reduction methods used to train and test model performance with execution time taken on the CICIDS2017 dataset to reduce the time complexity and enhance performance to detect intrusion by experiment and leveraging feature engineering techniques like PCA (Principal Component Analysis), LDA (Linear Discriminant Analysis), t_SNE (t-Distributed Stochastic Neighbor Embedding), and Autoencoders. This framework also resolves the class imbalance issues by using SMOTE (Synthetic Minority Oversampling Technique), generates synthetic samples of those classes, which have a very low number of samples to balance the class for a better model performance. Our comparative analysis is performed on metrics like accuracy, training time and memory usage for machine learning models like Gradient Boosting, Logistic Regression, XGBoost and deep learning models. DL with LDA feature engineering approach achieved the highest test accuracy of 95.99% and Gradient Boosting shows strong performance by attaining a high-test accuracy of 90.8%. Illustrated DL model had higher memory usage, but LR and XG- Boost models performed computationally efficient. Further, it is observed that LDA performed better with ML and DL models in comparison to other feature engineering techniques to enhance the intrusion detection efficiency.

Read More

Doi: https://doi.org/10.54216/JCIM.160105

Vol. 16 Issue. 1 PP. 53-67, (2025)

An Empirical Investigation on the Origins and Effects of Cybersecurity Culture in It Organizations

Balamuralikrishna Thati , Ravi Kiran Koppolu , D. Lokesh Sai Kumar , Tenali Nagamani , P. Muthukumar , S. Lalitha

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.

Read More

Doi: https://doi.org/10.54216/JCIM.160106

Vol. 16 Issue. 1 PP. 68-85, (2025)

Innovative Resilient Systems Scheduling Methods for Explicit Critical Applications in Cloud Environments

Adel A. Alyoubi

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.

Read More

Doi: https://doi.org/10.54216/JCIM.160107

Vol. 16 Issue. 1 PP. 86-98, (2025)

Biometric Data Securement Using Visual Information Encryption

Sawsan D. Mahmood , Hadeel M Saleh , Asraa Y. Youssef , Lara Ahmad Ghasab Almashagba , Fathiya Al Abri

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.

Read More

Doi: https://doi.org/10.54216/JCIM.160108

Vol. 16 Issue. 1 PP. 99-106, (2025)

A Robust Disease Prediction System Using Hybrid Deep Neural Networks

K. Tharageswari , N. Mohana Sundaram , R. Santhosh

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.

Read More

Doi: https://doi.org/10.54216/JCIM.160109

Vol. 16 Issue. 1 PP. 107-119, (2025)

Dynamic Leader Sibha Algorithm (DLSA): A Novel Hierarchical Metaheuristic Approach for Solving Engineering Design Problems

El-Sayed M. El-kenawy , Amel Ali Alhussan , Doaa Sami Khafaga , Amal H. Alharbi , Sarah A. Alzakari , Abdelaziz A. Abdelhamid , Abdelhameed Ibrahim , Marwa M. Eid

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.

Read More

Doi: https://doi.org/10.54216/JCIM.160110

Vol. 16 Issue. 1 PP. 120-133, (2025)

A Swarm Inspired Chaotic Map Evoked Attribute Encryption Framework Using Multi-Model Inputs in Cloud Environment

A. Jeneba Mary , K. Kuppusamy , A. Senthilrajan

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

Read More

Doi: https://doi.org/10.54216/JCIM.160111

Vol. 16 Issue. 1 PP. 134-150, (2025)

Adversarially Robust 1D-CNN for Malicious Traffic Detection in Network Security Applications

Baraa Mohammed Hassn , Esraa Saleh Alomari , Jaafar Sadiq Alrubaye , Oday Ali Hassen

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.

Read More

Doi: https://doi.org/10.54216/JCIM.160113

Vol. 16 Issue. 1 PP. 162-175, (2025)

Modify Block Chain Environment based on Post-quantum Algorithms

Rasha Hani Salman , Hala Bahjat Abdul Wahab

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

Read More

Doi: https://doi.org/10.54216/JCIM.160112

Vol. 16 Issue. 1 PP. 151-161, (2025)

Computer Vision of Smile Detection Based on Machine and Deep Learning Approach

Huda Lafta Majeed , Oday Ali Hassen , Dhyeauldeen Ahmed Farhan , Yu Yu Gromov , Kavita Sheoran , Geetika Dhand

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.

Read More

Doi: https://doi.org/10.54216/JCIM.160115

Vol. 16 Issue. 1 PP. 208-230, (2025)

A New Automated System Approach to Detect Digital Forensics using Natural Language Processing to Recommend Jobs and Courses

Shahlaa Mashhadani , Rajaa Mrayeh Mohammed , Nishtha Jatana , Charu Gupta , Oday Ali Hassen , Shweta Jindal

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.

Read More

Doi: https://doi.org/10.54216/JCIM.160116

Vol. 16 Issue. 1 PP. 231-242, (2025)

Enhanced Malware Classification: A Hybrid Model Utilizing Denoising Autoencoder and CNN based on visualization method

Thippireddy Harika , Gera Pradeepini

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.

Read More

Doi: https://doi.org/10.54216/JCIM.160117

Vol. 16 Issue. 1 PP. 243-251, (2025)