Publication Search

Explainable artificial intelligence (XAI) has become a critical requirement in cybersecurity due to the high-stakes nature of security decision-making and the limitations of black-box learning models. This study investigates the construction of an explainable cybersecurity knowledge representation by leveraging standardized terminology from the NIST cybersecurity glossary. The primary problem addressed is the lack of transparent and semantically grounded reasoning mechanisms in existing AI-driven cybersecurity systems, which limits trust, accountability, and analyst adoption. To address this challenge, we propose a NIST-based semantic knowledge graph that embeds explainability directly into its ontology structure and reasoning process. The proposed framework systematically extracts definitional entities and relations from NIST glossary entries to construct a domain ontology and a multi-relational knowledge graph. A rule-based semantic relation extraction method is employed to ensure faithful, interpretable, and reproducible reasoning paths. The resulting knowledge graph contains over 3,000 cybersecurity concepts and approximately 27,000 semantic relations, covering hierarchical, associative, dependency, and mitigation semantics. Experimental evaluation demonstrates that the proposed approach achieves a high level of explainability, with 92.4% of reasoning outcomes being fully traceable and only 1.4% classified as non-traceable. Most explainable reasoning paths are limited to two or three hops, indicating an effective balance between inferential depth and human interpretability. Structural analysis further confirms the presence of meaningful hub concepts that support multi-hop semantic inference. These results confirm that ontology-driven, standard-based knowledge graphs provide a robust foundation for explainable cybersecurity intelligence. The study concludes that explainability-by-design, grounded in authoritative standards, offers a viable and trustworthy alternative to opaque AI models for cybersecurity applications.

The increasing sophistication of cyber threats has rendered traditional cybersecurity models insufficient in safeguarding enterprise networks. This study introduces a risk aware cybersecurity governance model that integrates real time threat intelligence with predictive anomaly detection to proactively mitigate potential threats. By leveraging advanced machine learning and AI techniques, the model enhances the ability to identify and address cyber threats before they can escalate into significant incidents. The model’s ability to predict anomalies, analyze real time threat intelligence feeds, and provide early warnings allows for faster response times and reduced risk exposure compared to traditional reactive models. Through simulations and real-world use cases, the proposed model demonstrated a 30% reduction in response time and a 25% decrease in overall risk exposure, showing its potential to improve security decision-making and resilience in dynamic threat environments. Unlike traditional models that rely on static rules and periodic policies, the proposed model uses predictive analytics to stay ahead of evolving threats, ensuring continuous monitoring and rapid adaptation. This proactive approach enhances organizational resilience, particularly in handling sophisticated cyber threats such as ransomware, malware, and phishing attacks. Despite its effectiveness, challenges such as data overload, scalability, and the need for interpretability in AI models remain. Future research will focus on refining predictive models, improving scalability for larger networks, and enhancing the explainability of machine learning models to foster greater trust in automated cybersecurity systems. This study contributes to the ongoing evolution of cybersecurity governance by demonstrating the value of integrating predictive and real time monitoring technologies for enhanced threat detection and mitigation.

Steganography is a technique for hiding secret data within digital media such as images, audio, and video without causing noticeable visual changes. In video media, this technique offers advantages because each frame can be utilized dynamically, resulting in a larger data embedding capacity. However, conventional methods such as fixed-number Least Significant Bit (LSB) embedding still face limitations in balancing visual quality, embedding capacity, and resistance to compression or noise. To address these challenges, this study proposes an Adaptive Video Steganography Method based on Multi-Bit LSB that employs brightness, texture, and motion analysis for each frame to determine the number of embedding bits adaptively. The system adjusts the embedding capacity according to the local characteristics of the video: areas with high texture or rapid motion are assigned more bits, while static or low-texture areas use fewer bits to preserve visual quality. After the embedding process, the video quality is evaluated using PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index Measurement) to assess its similarity to the original video. Experimental results show a PSNR value of 45.86 dB and an SSIM value of 0.9441, Thus, the proposed adaptive method proves to be efficient, robust against disturbances, and capable of maintaining data security without compromising visual quality, making it highly suitable for implementation in multimedia-based information security systems.

The integration of cloud computing and data security systems is vital for the operational success and competitiveness of fintech startups. Cloud computing enables these startups to scale quickly, manage resources efficiently, and reduce infrastructure costs, making it an indispensable tool for businesses in the rapidly evolving fintech sector. However, with the benefits come significant challenges, particularly in data protection and cybersecurity. As fintech services handle sensitive financial data, ensuring robust security measures such as encryption, access controls, and continuous monitoring is crucial to maintaining user trust. Furthermore, regulatory compliance, both local and global, adds complexity to the data protection strategies of fintech companies. This research explores the key factors that drive cloud adoption in fintech, the security challenges associated with cloud environments, and the strategies implemented by startups to address these challenges. Interviews with IT managers from Indonesian fintech startups reveal that while cloud computing offers scalability and cost-effectiveness, issues like compliance with local regulations and the protection of sensitive data remain major concerns. The research suggests that fintech startups should invest in both cloud infrastructure and advanced cybersecurity measures to protect their operations and customer data. Additionally, creating a comprehensive roadmap for regulatory compliance and fostering partnerships with cybersecurity firms will help mitigate risks and ensure long-term success. The findings highlight the importance of integrating cloud computing with effective security strategies to navigate the complex regulatory and security landscape of the fintech industry.

This research has a purpose to determine the effect of online transaction security on purchasing decisions through the Shopee application. The respondents consisted of 74 students from the Digital Business Study Program at Universitas Amikom Purwokerto who actively use Shopee. This research employed a quantitative descriptive method with simple linear regression analysis. The results indicate that online transaction security has a positive and significant effect on purchasing decisions, with a regression coefficient of 0.887 and a significance value of 0.000. The coefficient of determination of 35.2% shows that transaction security contributes to purchasing decisions, while the remaining percentage is influenced by other factors. The higher the level of security perceived by consumers during online transactions, the greater the likelihood of making a purchase. These findings highlight the importance of improving security systems and information transparency on e-commerce platforms such as Shopee to create a safe, comfortable, and trustworthy shopping experience for users.

In the digital era, the demand for practical and efficient security systems has significantly increased, particularly in the context of access control for restricted rooms or buildings. This research aims to develop an automatic door locking system utilizing an RFID card and a NodeMCU ESP32 microcontroller integrated with Internet of Things (IoT) technology through real-time notifications using the Telegram application. The system is designed to replace conventional locking methods that often present various weaknesses, such as key loss, physical duplication, and lack of remote access capabilities. The development method employed is the Research and Development (R&D) approach, consisting of needs analysis, system design, hardware and software implementation, followed by testing and evaluation. The main components used in the system include the RC522 RFID reader for user identification, Espressif manufactures the ESP-32 microcontroller, which is equipped with Wi-Fi and Bluetooth modules to enable wireless internet connections. NodeMCU ESP32 as the control center and internet connector, a relay module as an electronic switch, and a solenoid door lock as the actuator. The results show that the system is capable of accurately reading RFID card UIDs, granting access to registered cards, activating the solenoid to unlock the door, and sending access status notifications to Telegram in an average of less than three seconds. The system also effectively denies access to unregistered cards and sends warning messages accordingly. Therefore, this system enhances the security and efficiency of room access control and has the potential to be adopted as a prototype solution in the development of smart homes or modern access control systems.

This systematic literature review examines the philosophy of science approaches to user security in distributed devices, such as IoT and Federated Learning. The review was conducted in response to the exponential growth of connected devices and the increasing security threats, including cyberattacks, data breaches, and unauthorized access. As distributed systems become more complex, traditional security approaches, such as cryptography and differential privacy, are often insufficient to address the ethical, philosophical, and contextual challenges that arise in these ecosystems. Distributed devices, especially in IoT and Federated Learning contexts, rely on vast amounts of personal data. This data, often stored or processed in decentralized environments, creates significant risks to user privacy and system integrity. As the number of connected devices grows, security risks multiply, creating challenges in maintaining user trust, privacy, and overall system resilience. Conventional techniques, such as encryption, only focus on technical aspects, often neglecting the deeper philosophical dimensions, such as the nature of knowledge, privacy, and fairness in these systems. These gaps highlight the need for a more nuanced approach that incorporates philosophical perspectives into security frameworks. This study uses a systematic literature review method based on the PICOC (Population, Intervention, Comparison, Outcome, Context) framework to analyze the relevance of epistemology, ontology, and ethics in strengthening system security. By examining the foundational principles of how knowledge is constructed (epistemology), what entities exist in the system (ontology), and the ethical considerations around data and user privacy (ethics), the review provides a comprehensive understanding of how philosophical concepts can be integrated into the design and implementation of security systems in distributed environments. The results reveal that epistemological principles, such as the verification and validation of data sources and models, can significantly improve the reliability and trustworthiness of distributed systems.  

This study aims to analyze customer satisfaction with the Byond by BSI service at PT Bank Syariah Indonesia Tbk KCP Palembang KM 6, focusing on the influence of service quality and security. The research population consisted of 2,800 customers, with a sample of 97 respondents selected through purposive sampling. A quantitative approach was employed, using a structured questionnaire as the primary data collection instrument. The collected data were analyzed using multiple linear regression, accompanied by instrument testing, classical assumption testing, as well as t-test, F-test, and the coefficient of determination (R²). The findings reveal that both service quality and security have a significant impact on customer satisfaction, both partially and simultaneously. The results indicate that customer satisfaction is not only determined by responsive, accurate, and accessible service quality but is also strongly influenced by the reliability of the security system provided. The regression coefficient shows that security has the most dominant effect, with a value of 0.427, which is higher than the influence of service quality. This highlights that the sense of safety in conducting digital transactions is the primary concern for customers when using Byond by BSI services. The implications of this study emphasize the importance for banks to continuously improve the quality of digital services, particularly in terms of responsiveness, speed of access, and ease of use of the application. In addition, strengthening digital security mechanisms, including customer data protection, transaction encryption, and early detection of potential cyber threats, is crucial in building and maintaining customer trust. The study further underlines the need for continuous improvement in both service quality and security systems as a key strategy to address the challenges of digital banking transformation in an increasingly competitive environment. Therefore, this research contributes to the development of Islamic banking management strategies that focus on customer satisfaction and loyalty in the digital era.

The rise in motor vehicle theft cases in various regions indicates the weakness of the security systems implemented by most users. Systems such as manual locks and alarms often fail to prevent crime, either because they are easily hacked conventionally or due to user negligence in their operation. In today's technological era, a system is needed that is not only secure, but also intelligent and practical. One promising solution is the implementation of a facial recognition-based security system. This study aims to design and test a vehicle security simulation system using facial recognition technology integrated with Arduino Uno and MATLAB. This system utilizes a laptop camera to capture the user's facial image, then performs a detection and verification process using the FaceNet algorithm. If the face is recognized and verified with data stored in the database, the Arduino will activate the actuator components in the form of a DC motor to simulate starting the engine, and a servo motor to simulate opening the vehicle door. This study uses a quantitative experimental approach to analyze the effect of variations in distance (30, 40, and 50 cm) and lighting brightness levels (10–20, 21–30, and 31–40 lux) on the system's response time. A total of 27 combinations of conditions were tested, and the data obtained were analyzed using Microsoft Excel and ANOVA tests in Minitab software. The results of the analysis showed that the optimal response time was obtained at a distance of 40 cm with a medium level of illumination (21–30 lux). In addition, both distance, brightness, and the interaction between the two factors were shown to have a significant effect on the system's response time (P-Value < 0.05). These findings indicate that the system is quite sensitive to environmental changes, so further testing is highly recommended, especially to measure the actual delay, the detection error rate, and the development of a more robust face detection algorithm so that the system can be used reliably in various lighting conditions and face capture angles in the real world.

The increasing vulnerabilities of modern enterprise network security systems highlight the necessity of adopting a more comprehensive and adaptive security approach than traditional VPN infrastructures. This study explores the design and implementation of Zero Trust Network Access (ZTNA) using the Cloudflare platform at PT FHI, focusing on addressing the weaknesses caused by uncontrolled remote access and legacy security models. The research adopts an experimental methodology based on the Network Development Life Cycle (NDLC), which includes systematic phases such as needs analysis, architectural design, system implementation, testing, and performance evaluation. Data were collected through structured interviews with IT managers and security specialists, direct observation of network logs, and comprehensive testing involving three different categories of end users. The findings demonstrate significant improvements in role-based access control, granular authentication, and the elimination of unrestricted access to internal resources. Additionally, real-time monitoring and alerting features available through the Cloudflare dashboard enhance visibility and responsiveness to potential threats. The implemented system successfully applies the “never trust, always verify” principle by blocking unauthorized access attempts, enforcing continuous validation, and producing detailed audit logs. Performance evaluation results confirm stable connections, acceptable latency for critical business applications, and an overall improvement in network security posture while maintaining operational productivity across departments..

In the modern era, the need for sophisticated vehicle security systems is increasing along with the high rate of motor vehicle theft. This research designs and implements a fingerprint sensor-based vehicle security system using an Arduino Uno microcontroller. This system aims to improve security by utilizing biometric technology that can only be accessed by verified users. The fingerprint sensor is used to recognize the user's fingerprint, then activate the system through a relay instead of a conventional key. System testing shows a fast response time with an estimated rise time of about 0.5 seconds and settling time of about 2 seconds, without any misidentification (false positive or false negative). Thus, the system is proven to provide higher security, good authentication speed, and ease of use compared to conventional security systems. These results show that the implementation of biometric technology in vehicles has the potential to be widely applied.

This study aims to analyze the legal protection of personal data subjects in the case of the 2024 data breach at the Temporary National Data Center (PDNS) managed by the Ministry of Communication and Informatics (Kominfo), based on Law Number 27 of 2022 on Personal Data Protection. The research employs a normative juridical method with a case study approach and statutory analysis. Legal materials are obtained from primary and secondary sources using literature research techniques. The findings reveal that Kominfo, as a public body and personal data controller, has not fully fulfilled its obligations to protect personal data as mandated by the law, as reflected in weak security systems, lack of transparency, and slow response to the breach incident. This study highlights the urgent need for the establishment of implementing regulations and an independent supervisory institution to ensure the effective protection of personal data for the public in Indonesia.

The increasing number of motorcycle thefts in various regions indicates that conventional security systems are not yet fully effective in protecting vehicles, necessitating new technology-based innovations. This study discusses the planning and implementation of a motorcycle security system utilizing Radio-Frequency Identification (RFID) technology as a more responsive and modern solution. The system is designed using a passive RFID tag placed on the motorcycle key, an RFID reader integrated with the motorcycle unit, and an Arduino microcontroller that functions to control the ignition system. With this combination, the motorcycle can only be activated if the appropriate tag is detected, while access attempts using an invalid tag or the loss of the tag will automatically disconnect the ignition system. Test results announced that tag recognition can be done very quickly, in less than a second, so as not to disrupt the user's comfort when starting the vehicle. In addition, this system is able to maintain consistent performance by providing an automatic response that supports advanced security. The implementation of this plan is expected to reduce motorcycle theft by providing an additional layer of security that is more difficult to penetrate than a manual key system. From the user's perspective, this technology remains practical because it does not require complicated procedures in its operation, simply by ensuring the appropriate RFID tag is attached to the motorcycle key. Overall, this research confirms that the application of Arduino microcontroller-based RFID technology can be an alternative, inexpensive, and applicable security system in everyday life. It is hoped that this system will not only improve protection for vehicle owners but also serve as a benchmark for the development of more sophisticated transportation security technologies in the future. Implementation of this system is expected to reduce motorcycle theft and provide a greater sense of security for vehicle owners.

Maritime security in Indonesia faces numerous challenges, including piracy, smuggling, and environmental degradation that threaten the sustainability of the maritime sector. Blockchain technology, known for its transparency, security, and efficiency, presents a potential solution to enhance maritime security systems in Indonesia. This study explores the application of Blockchain technology in improving surveillance, tracking, and data validation in the maritime sector. By analyzing existing literature and case studies, the research identifies how Blockchain can strengthen security systems through smart contracts, real-time supply chain tracking, and increased transparency in maritime transactions. The study also discusses the challenges of implementing Blockchain technology in Indonesia's maritime sector and offers recommendations to accelerate its adoption. The findings aim to provide insights for policymakers and practitioners in developing technology-driven solutions to enhance maritime security in Indonesia.

The rapid advancement of digital technology has led to significant changes in how people conduct financial transactions, particularly the shift from cash payments to digital methods that are viewed as more efficient, faster, and safer. This study aims to analyze differences in the frequency of using three types of financial transactions cash, e-wallets, and bank transfers in daily life. A quantitative descriptive-comparative approach was applied, involving 47 respondents selected through purposive sampling. The instruments were tested for validity and reliability before analysis. Data were examined using the Friedman test to assess differences in usage frequency among the three methods. The findings show a significant difference in frequency, with e-wallets being the most used, followed by bank transfers, and then cash. These results suggest that people now prioritize convenience, speed, and accessibility in financial activities. The implications highlight the need for financial institutions and payment providers to enhance digital security systems and improve service accessibility. Small business operators are encouraged to adapt to changing consumer preferences that increasingly favor digital payments. Furthermore, improving digital financial literacy is essential to support broader financial inclusion. This study also provides recommendations for policymakers to expand access to digital financial services, especially for underserved communities.

Automatic object detection is one of the crucial aspects in the field of digital image processing that plays a vital role in various modern applications, ranging from security systems to pattern recognition in medical and industrial fields. This study aims to implement an automatic object detection method with a digital image representation-based approach using MATLAB software. The main focus is directed at the pixel-based image processing process, where each image element is processed to extract relevant visual information. In this study, stages are carried out starting from image acquisition, color conversion, image quality enhancement, threshold-based segmentation, to extraction of targeted object features. Digital images are analyzed through transformation into grayscale and binary forms to facilitate the detection process. The use of MATLAB provides flexibility in numerical and visual data processing, and supports various efficient image processing libraries.

The Bogor City Scout Movement Branch Office is still experiencing problems in administrative management, including cumbersome manual filing processes, unresponsive disposition of incoming letters, excessive paper consumption, and vulnerable financial document security systems. This research aims to propose the implementation of the E-Office system as an innovative solution for administrative transformation towards a more efficient and digitally integrated system. The research method used is a descriptive qualitative approach by collecting data from interviews with three key informants who have an active role in operations and administration at the Bogor City Scout Movement Branch. The results show that the use of E-Office has excellent potential to improve operational efficiency, increase document security, and speed up administrative processes. However, the implementation of E-Office requires special training and changes for employees who still use the manual system. 

Image processing is a branch of computer science that is growing rapidly and is widely used in various fields, including in security systems. Face identification is one of the main applications of image processing that aims to recognize and distinguish individual faces in a system. The methods used in face identification involve various techniques, such as facial feature detection, characteristic extraction, and classification using machine learning algorithms. This article discusses the application of image processing in a security system based on face identification and the technology used to improve the accuracy and reliability of the system. The results of the study show that the combination of deep learning algorithms with image pre-processing techniques can increase the success rate of face identification in security systems.

This study aims to evaluate the effectiveness of the book lending policy at the Digital Library of the State University of Medan (UNIMED) and explore student responses to the policy. The method used is a qualitative descriptive approach, with data collection through interviews and observations in the Digital Library building. The results of the study show that most students understand and feel helped by the new policy that requires the use of digital applications for book borrowing, which is considered to improve accessibility and convenience. However, there are concerns about the security of personal data, as well as dissatisfaction regarding the withdrawal of physical library cards. Overall, while this policy is effective, there is still a need for improvement, especially in the aspects of data security and better socialization. The proposed recommendations include improving security systems, more intensive policy socialization, and the development of additional in-app features to improve the user experience.

GoSend as an instant delivery service from Gojek plays an important role in meeting the demand for fast and reliable delivery. However, there are still challenges in terms of service quality, customer satisfaction, and competitiveness in the digital logistics industry. This study analyzes GoSend's electronic service quality attributes using the Kano Model to identify the factors that most influence customer satisfaction. The quantitative method is applied through a survey of 206 GoSend users in Semarang, with the integration of E-Servqual indicators and Kano Model attributes. The results of the study show that most service attributes fall into the "Indifferent" category, meaning they do not have a significant effect on customer satisfaction. However, attributes such as transaction data security and item conditions fall into the "One-Dimensional" category, so improvements in these aspects can increase customer satisfaction. The analysis of the Extent of Satisfaction (EOS) and Extent of Dissatisfaction (EOD) shows that responsiveness to complaints and service personalization still need to be improved. Based on these findings, strategic recommendations that can be given are increasing customer service responsiveness, optimizing compensation policies, and strengthening security systems to increase customer trust. The integration of the Kano Model with E-Servqual provides a comprehensive evaluation of the quality of digital logistics services while also being a guide for GoSend in increasing customer satisfaction and loyalty amidst increasingly fierce competition.