Asian Journal of Research in Computer Science
Not a member yet
792 research outputs found
Sort by
Open Data for Cyber Resilience: An Analysis of Public-private Collaboration in AI-Supported Threat Intelligence Sharing
No full textThis study explores how open threat intelligence data and artificial intelligence (AI) can jointly enhance cybersecurity resilience and innovation through structured public-private collaboration. As cyber threats become increasingly complex and transnational, the need for coordinated intelligence sharing between government and private institutions has never been more urgent. This research builds on Okunleye’s empirical work linking open data to innovation and extends it into the cybersecurity domain. Using open-access datasets from MITRE ATT&CK, Verizon’s 2024 Data Breach Investigations Report (DBIR), the OECD, and the EU Open Data Portal, the study evaluates how open CTI (Cyber Threat Intelligence) infrastructures enable AI-assisted threat detection, response, and governance. Employing descriptive statistics, multiple linear regression, moderation analysis, and principal component analysis (PCA), the study finds that public institutions consistently outperform private ones in CTI readiness. AI collaboration improves breach detection speed by 25.63 units, reduces incident response time by 52.11 units, and enhances containment effectiveness by 31.24 units. Additionally, AI significantly amplifies the innovation gains derived from public-private collaboration. Key structural barriers identified include legal restrictions, data localization, and technical formatting inconsistencies. The study proposes a Collaborative Cyber Resilience Model (CCRM) that integrates open data standards, AI systems, and regulatory cooperation to support secure and scalable threat intelligence sharing. This research offers practical insights for cybersecurity policymakers, operational leaders, and researchers seeking to understand and implement resilient, AI-enabled CTI frameworks across sectors
AI-Driven Cyber Threat Detection for Securing National Critical Infrastructure
No full textThis research explores the application of Artificial Intelligence (AI) in enhancing cyber threat detection mechanisms aimed at protecting national infrastructure. The purpose of the study is to evaluate how AI-driven approaches, particularly machine learning and deep learning techniques, can improve the speed, accuracy, and adaptability of cybersecurity systems in the face of increasingly sophisticated and persistent threats targeting critical sectors such as energy, transportation, water, and communications.
The methodology involves a comparative analysis of traditional signature-based detection systems versus AI-enhanced models using real-world datasets and simulated cyber-attack scenarios. The study utilizes supervised and unsupervised learning algorithms, including neural networks and anomaly detection frameworks, to assess performance across detection rate, false positive rate, and response time.
Key findings indicate that AI-enhanced systems significantly outperform traditional methods in early detection of zero-day attacks, adaptive threat response, and overall threat landscape analysis. Additionally, AI models demonstrate improved scalability and resilience in handling high-volume, high-velocity network traffic.
The research concludes that the integration of AI into national cybersecurity infrastructure provides a transformative capability for proactive defense. However, it also highlights the need for continuous model training, ethical oversight, and hybrid human-AI decision frameworks to mitigate risks such as algorithmic bias and adversarial manipulation
Evaluation of Information Security Practices in the Context of Digital Transformation
No full textDigital transformation is accelerating the adoption of cloud platforms, data-intensive services and IoT ecosystems, reshaping the attack surface organisations must defend. This study provides an integrated assessment of information-security maturity in that context. Using a multi-method design—systematic literature review, cross-sector case studies, comparative analysis of leading maturity frameworks (NIST CSF, COBIT, CMMI, CMAF), and an expert survey—we gauge how well current controls, processes, and cultures align with emerging risks. Quantitative benchmarking indicates that enterprises operating at maturity levels 4–5 experience ≈50 % fewer major breaches than peers at levels 1–3, yet fewer than one-third routinely rehearse cloud- and IoT-oriented attack scenarios, exposing a persistent threat–readiness gap. To bridge this gap, the paper proposes an adaptive governance model that couples zero-trust principles and ML-driven analytics with continuous risk appraisal and culture-centric interventions. The findings inform security leaders and policymakers where to prioritise investment, emphasising that sustained digital growth depends on embedding cybersecurity maturity as a core metric of organisational resilience
Global Trends in AI-Driven Cybersecurity: A Systematic and Bibliometric Analysis
No full textThis study investigates global trends in artificial intelligence (AI)-driven cybersecurity through a combined systematic literature review and bibliometric analysis of publications from 2015 to 31st July, 2025. As digitalisation accelerates and cyberattacks become increasingly sophisticated, AI has emerged as a transformative tool for threat detection, prevention, and response. The review identifies four core domains where AI applications are most prominent: anomaly-based intrusion detection systems, automated malware analysis, phishing and social engineering prevention, and Security Orchestration, Automation, and Response (SOAR). In these areas, machine learning and deep learning techniques, particularly convolutional and recurrent neural networks, autoencoders, and transformer-based models demonstrate superior performance in detecting complex, evolving threats compared to traditional rule-based approaches. The bibliometric analysis reveals exponential growth in research output since 2015, with a sharp rise between 2021 and 2023, coinciding with breakthroughs in generative AI, deep learning, and the increased cyber risks linked to the COVID-19 digitalisation surge. Citation patterns highlight the growing applied relevance of post-2020 research, while thematic evolution indicates a shift toward adversarial AI, federated learning, and zero-trust architectures. Despite significant advances, challenges persist around explainability, governance, dual-use risks, and global disparities in research capacity. This study underscores AI’s central role in shaping the future of cybersecurity while emphasising the need for ethical frameworks and equitable global participation in technological adoption
Empirical Study of Contrast Enhancement Techniques for Handicraft Bell Metal Product Images
No full textHandicraft Bell metal products hold great cultural and artistic importance in Assamese society, especially in the Sarthebari region, where they are crafted using traditional techniques passed down through generations.However, studying and classifying images of these intricate products using modern machine learning methods comes with challenges. Variations in pixel intensity, caused by changes in brightness and color during photography, can lower image quality. Additionally, the detailed textures and complex backgrounds of these products make it difficult for computers to separate the main object from its surroundings. A dataset of fifty handicraft bell metal product images was collected directly from production units in Sarthebari area using digital camera. Image pre-processing is essential to increase the model performance. This study examines five contrast enhancement techniques-Histogram Equalization (HE), Adaptive Histogram Equalization (AHE), Unsharp Masking (UM), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Triangular Fuzzy Membership Contrast Limited Adaptive Histogram Equalization (TFM-CLAHE). The performance of these techniques was evaluated using four quantitative metrics: Mean Squared Error (MSE), Signal-to-Noise Ratio (SNR), Peak Signal-to-Noise Ratio (PSNR), and Similarity Index (SI) . The results show that UM and TFM-CLAHE are the most effective methods for enhancing image details while maintaining clarity. These techniques help to highlight the intricate designs of bell metal products, making them useful for automated classification and quality control. By applying these methods, technology can better support the preservation and promotion of this ancient Assamese craft
Advancing Hybrid Numerical Methods for Nonlinear Stochastic Differential Equations: Applications in Complex Systems
No full textThe focus of this work is to consider composite numerical techniques for the approximation of SDEs with nonlinear coefficients in the drift and diffusion terms. SDEs, crucial for modeling systems with stochastic components, contain nonlinear terms that cause analytical solvability, numerical stiffness, and sensitivity to noise. These difficulties pose a problem for traditional techniques such as Euler-Maruyama or Milstein schemes, specifically in stiff or very nonlinear systems. Accompanying exact methods are numerical methods that include a deterministic synthesis of drift terms and a stochastic interpolation of diffusion terms with the purpose of increasing precision and stability and optimizing used computing time. Discussed approaches include implicit-explicit (IMEX) schemes, spectral collocation methods, and machine learning-assisted techniques. IMEX methods handle stiffness in nonlinear drift terms implicitly, while explicitly handling stochastic diffusion. Spectral-collocation methods utilize high-order polynomial approximations for accuracy in discretization where solutions are smooth and defined in a bounded domain. The combination of these techniques and machine learning extends SDE analysis and concentrates on SDE nonlinearities as well as adaptive solution strategies. They find use in every area of discipline, such as stochastic volatility models in finance, population dynamics in biology, and turbulent fluid flows in engineering. Simulation results show that hybrid schemes outperform other methods in terms of accuracy, stability, and computational expense. This work outlines how the integration of the suggested methods can overcome the shortcomings of the classic approaches so as to enable progression in solving complex, high-dimensional, and nonlinear stochastic problems. Subsequent studies will continue to investigate additional adaptive frameworks and more domain-specific and machine learning-based improvements to expand the spectrum of hybrid use
Cyber Espionage in the Age of Artificial Intelligence: A Comparative Study of State-Sponsored Campaign
No full textThis study investigates the transformative role of artificial intelligence (AI) in state-sponsored cyber espionage, focusing on its dual use in offensive and defensive operations. Using data from the MITRE ATT&CK Framework, FireEye APT Groups Database, UNSW-NB15 Intrusion Detection Dataset, and the Cyber Conflict Tracker by CFR, this research applied network graph analysis, multi-criteria decision analysis (MCDA), ensemble classification models, and Difference-in-Differences (DiD) analysis. Results revealed that AI-driven offensive techniques, phishing (degree centrality 0.85), and adaptive malware (betweenness centrality 0.81) significantly enhance operational precision and scalability. Defensively, ensemble classification models achieved up to 95.8% accuracy, highlighting AI\u27s efficacy in intrusion detection. AI regulatory frameworks reduced misattribution rates by 20% and escalation incidents by 10%, demonstrating their critical role in mitigating geopolitical risks. The findings impress AI\u27s transformative potential in advancing cyber operations and shaping international policy and governance. By addressing challenges such as attribution, escalation risks, and ethical dilemmas, this study highlights the necessity for stronger global cooperation and regulatory frameworks to navigate the dual-use nature of AI, providing actionable insights for policymakers, cybersecurity professionals, and researchers, emphasizing the urgency of aligning technological advancements with strategies for enhancing global cybersecurity resilience
The Role of Machine Learning in Enhancing Cybersecurity
No full textThe advancement of information technology is rapidly changing the face of cyber security and this makes it more important with the increasing trend of sophistication of cyber threats in the society. The authors in this research aim at analyze how AI and ML can improve cybersecurity capabilities and how these technologies can be employed to prevent cyber-attacks in real-time. By examining a few well-known cyber episodes – the SolarWinds attack and the Colonial Pipeline hack – in an exploration of the future of AI and machine learning in cybersecurity, the study underscores the potential for advancement along with the potential for obfuscation. Despite these benefits, these Integrated technologies come loaded with new risks, especially in matters concerning the ethical issues and future insecurities within the AI-based security systems. More specifically, this paper investigates the issue of maintaining the balance between the introduction of innovative technologies and the protection of networks, arguing that the only effective approach to combating modern threats is their combination and the implementation of layers based on traditional anti-virus programs and artificial intelligence. This discussion insists on the interdependence of governmental agencies, business entities, and academic organizations to mitigate growing new age cyber risks. Last but not the least, the study recommends that for the development of more resilience and ethical solutions towards AI for cybersecurity solutions, more research work has to be implemented in developing more robust cybersecurity models
Improving Website Usability with Design Thinking: A Case Study of BEM FMIPA Udayana University’s Website
No full textAims: This study aims to implement the Design Thinking methodology in the development of the BEM Faculty of MIPA, Udayana University’s company profile website. The primary objective is to enhance user experience by addressing usability issues and improving accessibility, navigation, and overall functionality.
Study Design: This research adopts a user-centered design approach, utilizing the Design Thinking framework, which consists of five phases: Empathize, Define, Ideate, Prototype, and Test.
Place and Duration of Study: This study was conducted at the Faculty of Mathematics and Natural Sciences, Udayana University, over a period of five months.
Methodology: The research study adopts a case study design and employs mixed methods, combining both qualitative and quantitative approaches. The research began with a quantitative preliminary usability evaluation using the System Usability Scale (SUS), where the existing website received a score of 51.75 (ranked F), indicating significant usability issues. In the next phase, qualitative data was gathered through surveys, interviews, and literature studies to identify user pain points, particularly related to website navigation, design, and content accessibility. The insights from these qualitative methods informed the redesign of the website. Using the principles of Design Thinking, the website was restructured with an emphasis on an intuitive interface, improved information hierarchy, and enhanced interactivity. Finally, the redesigned website prototype was subjected to usability testing to evaluate improvements and gather both qualitative and quantitative feedback.
Results: The implementation of Design Thinking resulted in significant improvements in user satisfaction and website efficiency. The SUS score rose from 51.75 to 88.96, indicating a major increase in usability. Efficiency tests showed a 28.36% improvement, with users requiring fewer clicks to complete tasks. These results highlight the new website\u27s enhanced intuitiveness, aesthetics, and alignment with user expectations.
Conclusion: The application of Design Thinking in website development successfully improved the usability and functionality of the BEM Faculty of MIPA company profile website. By adopting a user-centered approach, the redesigned website effectively addresses user needs, enhances accessibility, and provides a better overall experience. Future research may explore further refinements and the integration of advanced features to maintain long-term user engagement
Harnessing AI and Emerging Technologies for Sustainable Food Systems: Innovations in Automation and Intelligent Production
No full textThe global food system faces challenges in food security, environmental sustainability, and supply chain inefficiencies, with traditional methods struggling to meet demands while minimizing resource depletion and ecological impact. New approaches that integrate AI and new technologies must be developed to address the growing concerns of global food security and sustainability. This article reviews the potential progressive roles of automation, artificial intelligence, and renewable energy for maintaining sustainable practices, optimizing food production, and enhancing decision-making. Blockchain technology improves transparency and traceability in food supply chains. IoT-powered smart systems enable real-time monitoring of crops, livestock, and food storage conditions, optimizing resource usage. AI-driven developing algorithms enhance decision-making, automate agricultural processes, and improve food quality and safety. While renewable energy sources like solar-powered aquaponics and hybrid energy systems promote ecologically sustainable food production, robotics and 3D printing are developing agricultural processes. However, widespread adoption faces challenges such as high costs, infrastructure limitations, and regulatory barriers alongside these benefits. Future research should focus on enhancing AI-driven solutions, addressing scalability issues, and ensuring equitable access to these technologies across AI ethics, infrastructure, and regulatory framework