Publication Search

This study explores the role of artificial intelligence in strengthening cybersecurity threat detection frameworks for next-generation network environments. The rapid expansion of cloud computing, Internet of Things ecosystems, and distributed digital infrastructures has significantly increased cybersecurity risks and operational vulnerabilities. Traditional cybersecurity systems often struggle to detect sophisticated and evolving threats due to their dependence on static detection mechanisms. Using a qualitative research approach and content analysis method, this study examines recent developments in artificial intelligence, machine learning algorithms, and intelligent cybersecurity frameworks. The findings indicate that AI-driven cybersecurity systems improve real-time threat detection, anomaly identification, automated monitoring, and predictive security analysis. Machine learning technologies such as Random Forest, Support Vector Machine, and deep learning models demonstrate strong potential for enhancing intrusion detection accuracy and reducing false positive rates. The study also identifies critical challenges related to ethical governance, privacy protection, computational complexity, and adversarial attacks in AI-based cybersecurity systems

Data security in Electronic Medical Records (EMR) is a crucial issue in health information governance in Indonesia. This study evaluates the compliance of health facility information security systems with Ministry of Health Regulation (PERMENKES) No. 24 of 2022 and Personal Data Protection Law (UU PDP) No. 27 of 2022, and analyzes the impact of non-compliance on service quality and patient trust. The method employed is a systematic narrative literature review on the Google Scholar database (2023–2026) using the keywords "data security and privacy," "electronic medical records," and "CIA Triad," focusing on the implementation of Confidentiality, Integrity, and Availability. The four healthcare facilities examined have implemented controls such as role-based access control, Electronic Signatures (TTE), Virtual Private Networks (VPN), data encryption, and SSL/TLS protocols in accordance with PERMENKES provisions and Article 35 of the UU PDP. However, the effectiveness of implementation is hindered by weak authentication due to the use of simple passwords and excessively long auto-logout durations, the absence of comprehensive written standard operating procedures (SOPs), low staff compliance with security protocols, and minimal patient awareness regarding personal data protection rights. These weaknesses heighten the risk of patient data breaches as well as potential administrative sanctions and fines, and carry negative implications for service quality and public trust. Recommendations include strengthening internal security policies, developing written SOPs, providing continuous training for healthcare workers, implementing stronger authentication mechanisms (e.g., multi-factor authentication/MFA), and conducting patient awareness programs to ensure regulatory compliance and maintain public confidence.

This study aims to analyze the Cambodian government's efforts to address human trafficking from a human security perspective. It employs a qualitative descriptive approach, utilizing secondary data from relevant journals, reports, and academic publications. The findings indicate that human trafficking in Cambodia has evolved into a hub for digital-based fraud linked to transnational cybercrime networks. Victims face not only labor exploitation but are also coerced into participating in online fraudulent activities, such as romance scams. This surge in human trafficking is driven by weak law enforcement, high levels of corruption, low public digital literacy, and the rapid expansion of the online gambling industry and special economic zones, which serve as operational bases for criminal activities. The Cambodian government has implemented various measures regarding prevention, protection, and law enforcement through regulations, international cooperation, victim rescue operations, and anti-fraud campaigns. However, the effectiveness of these policies remains limited due to the state's constrained capacity and the ability of criminal networks to continuously adapt to advancements in digital technology. The study concludes that addressing human trafficking in Cambodia requires strengthened governance, more intensive international cooperation, and improved public digital literacy.

Recent Internet of Things (IoT) intrusion detection studies have reported near-perfect benchmark performance for Distributed Denial of Service (DDoS) detection, yet limited attention has been given to understanding how different traffic representations contribute to the detection process under highly imbalanced traffic conditions. This study presents an ablation-driven analysis to investigate the contribution of statistical and temporal representations for large-scale IoT DDoS detection using the CICIoT2023 dataset. Three experimental scenarios are evaluated, including statistical representation, temporal sequence representation, and hybrid statistical–temporal representation. Temporal representations are learned using a one-dimensional Convolutional Neural Network (1D-CNN) with lag-based traffic sequences, while ensemble tree-based classifiers are employed for final classification and representation analysis. In addition, multiple ablation configurations are designed to evaluate the impact of temporal dependency modeling and feature engineering strategies on detection performance. Experimental results show that statistical traffic representations remain highly effective for DDoS detection on CICIoT2023, achieving 99.36% accuracy and 99.31% weighted F1-score in the statistical representation scenario. Feature importance analysis further indicates that engineered statistical features contribute substantially more to the classification process than CNN-based temporal representations. Although temporal modeling captures sequential traffic behavior, its contribution is relatively limited and mainly acts as a complementary representation. Furthermore, the hybrid configuration produces only marginal improvements over the statistical representation alone. These findings highlight the importance of representation-level analysis for understanding the actual contribution of statistical and temporal modeling in modern IoT intrusion detection systems beyond relying solely on benchmark accuracy.

This study aims to examine how an online bajaj-based pick-up and drop-off service developed by a kindergarten is implemented. The bajaj application is considered an innovation in a community-based educational transportation system. The limitations of conventional pick-up and drop-off systems in providing optimal efficiency, transparency, and safety form the basis of this research. This study employed a qualitative approach using a case study method, with data collected through observation, interviews, and documentation. The results indicate that the use of the online bajaj application improves service quality through features such as booking services, real-time location tracking,and notifications to parents, which enhance time efficiency, transparency, and a sense of security. Compared to commercial transportation services, the community-based service model allows for more controlled operational management. However, challenges such as low digital literacy among users, limited network infrastructure, and potential data security risks were also identified. Critically, this innovation contributes significantly to the development of the smart mobility concept in the education sector, although it still requires improvement in terms of system sustainability and user data protection.

The rapid growth of the Internet of Things (IoT) has driven numerous innovations in wireless communications that not only demand technical efficiency but also raise philosophical questions about the nature of scientific knowledge. One such innovation is Physical Layer Network Coding (PLNC), a communication technique that utilizes signal interference as a source of information to enhance system performance. This paper examines the philosophical dimensions of science within PLNC, focusing on three fundamental aspects: ontology, epistemology, and axiology. Ontologically, PLNC represents a new paradigm in wireless communication that reinterprets interference not merely as noise but as an opportunity. Epistemologically, knowledge of PLNC is derived through scientific methods such as mathematical modeling, experimentation, and simulation—yielding intersubjective and verifiable truths. Axiologically, PLNC holds practical value in terms of energy efficiency, data reliability, and contributions to the sustainability of IoT ecosystems, while also raising ethical considerations regarding privacy and information security. Thus, this study demonstrates that the development of PLNC cannot be separated from philosophical reflection, emphasizing the profound interconnection between technological advancement, scientific methodology, and human values.

The increasing sophistication of malware has rendered traditional signature-based detection methods insufficient, necessitating behavior-driven and adaptive analytical frameworks. This study presents a sequential deep learning framework that models system-level API call sequences as structured linguistic representations for behavioral malware detection. Unlike conventional comparative studies, this work systematically evaluates recurrent and attention-based architectures under controlled experimental conditions, with a particular focus on generalization performance and overfitting mitigation. Two neural architectures, a Long Short-Term Memory (LSTM) network and a Transformer-based attention model, are trained on publicly available API call sequence data for binary classification of malicious and benign executables. Beyond standard accuracy metrics, the study further examines model stability, convergence behavior, and the impact of long-range dependency modeling on detection robustness. Experimental results demonstrate that the Transformer architecture achieves superior performance, attaining 95.54% classification accuracy and consistent improvements in precision, recall, and F1-score, indicating a stronger ability to capture complex behavioral dependencies. These findings highlight the effectiveness of attention mechanisms in behavioral malware modeling and provide empirical evidence that NLP-inspired architectures offer a robust and scalable approach for real-world cybersecurity applications.

Automatic facial expression recognition is a significant challenge in human-computer interaction with broad relevance in mental health, security, and behavioral analysis. This study proposes the implementation of Deep Learning using a custom Convolutional Neural Network (CNN) architecture to classify seven basic emotion categories: angry, disgust, fear, happy, sad, surprise, and neutral. Key challenges such as lighting variations and visual feature ambiguity in the FER2013 dataset are addressed through image pre-processing techniques, data augmentation, and the use of Batch Normalization and Dropout layers to prevent overfitting. The research methodology involves a systematic architectural design with three main convolution blocks optimized for computational efficiency. Experimental results show that the proposed model achieved a validation accuracy of 68.2%. Performance analysis based on F1-Score reveals that the "Happy" emotion has the highest detection rate (0.85) due to contrasting facial geometric features, while the "Fear" emotion is the most difficult class to identify (0.41). This study concludes that the use of an optimized standalone CNN architecture provides competitive and efficient performance compared to heavier transfer learning models, making it feasible for implementation on devices with mid-range hardware specifications.

Digital transformation has become a critical lever for modernizing maritime logistics, particularly in archipelagic nations where supply chain fragmentation poses persistent operational challenges. This study examines the integration of Internet of Things (IoT) and blockchain technologies as dual mechanisms for enhancing supply chain transparency within Indonesian domestic shipping networks. Employing a qualitative research design supported by thematic analysis, the study engaged maritime logistics experts, port operators, and shipping company representatives as primary respondents. Findings reveal that IoT-blockchain integration significantly improves real-time cargo visibility, reduces documentation fraud, and strengthens regulatory compliance across multi-port supply chains. The research further demonstrates that digital transformation in maritime logistics is not merely a technological upgrade but a governance and institutional reform imperative, particularly given Indonesia's strategic maritime position. Results indicate an overall high performance score across transparency, efficiency, and security indicators, affirming the readiness of key stakeholders to adopt integrated digital solutions. The study contributes a replicable framework for digital maritime logistics governance applicable to archipelagic developing economies seeking sustainable supply chain advancement.

The increasing complexity and scale of modern network traffic driven by IoT and cloud-based infrastructures have made accurate intrusion detection a critical challenge. Conventional network intrusion detection systems (NIDS) and many deep learning–based approaches struggle to reliably detect minority and stealthy attacks due to severe class imbalance and limited discrimination of subtle traffic patterns. To address these limitations, this study proposes a hybrid CNN–RBF–Attention framework for network intrusion detection. The proposed model integrates three complementary components: (i) a convolutional neural network for hierarchical feature extraction from network flow data, (ii) a radial basis function (RBF) network for localized nonlinear classification using prototype-based decision regions, and (iii) an attention mechanism that adaptively weights RBF activations to emphasize discriminative traffic patterns. SMOTE is applied exclusively to the training data to mitigate class imbalance. The framework is evaluated on the widely used CICIDS2017 and CICIDS2018 benchmark datasets in both binary and multiclass settings, using recall, precision, F1-score, confusion matrices, and ROC analysis. Experimental results demonstrate that the proposed hybrid model consistently outperforms standalone CNN and RBF baselines, particularly in terms of recall and F1-score. On the CICIDS2018 dataset, the model achieves 99.81% accuracy and 99.81% F1-score in binary classification, and 99.54% accuracy and 99.54% F1-score in multiclass classification. On CICIDS2017, it achieves 98.12% accuracy and 98.12% F1-score in binary classification, and 98.92% accuracy and 98.92% F1-score in multiclass classification. Confusion matrix and ROC analyses further show strong class separability and reliable performance in low–false-positive-rate regions, which is critical for real-world IDS deployment. These results confirm that combining deep hierarchical feature learning, localized prototype-based classification, and attention-guided refinement yields a robust, operationally reliable intrusion detection framework for highly imbalanced network environments.

Digital transformation in public services represents a strategic shift in integrating information technology into governmental administrative systems to enhance service efficiency, transparency, and accountability. One prominent innovation in this effort is the adoption of electronic land certificates initiated by the Ministry of Agrarian Affairs and Spatial Planning/National Land Agency (ATR/BPN) as part of land service modernization. This policy is formally regulated under Ministerial Regulation No. 3 of 2023 concerning electronic documents in land registration. This study employs a descriptive qualitative approach to examine the implementation process, identify enabling and constraining factors, and assess the impact of electronic land certificates on the quality of land services. Data were obtained through interviews, field observations, and document analysis at the Tulungagung Regency Land Office and analyzed using the interactive model proposed by Miles and Huberman. The findings indicate that electronic land certificates contribute significantly to improving service efficiency, administrative speed, and data security. Nonetheless, several challenges persist, including inadequate network infrastructure in rural areas, limited public digital literacy, and insufficient information technology personnel. Despite these constraints, the initiative has been positively received and reflects the local government’s commitment to advancing digital governance and good governance principles. The effectiveness of this transformation largely depends on institutional readiness, technological support, and community engagement.

The agricultural sector is a vital pillar in maintaining food security and enhancing the livelihoods of rural communities. In an effort to improve agricultural productivity, the Government of Lamongan Regency, through the Food Security and Agriculture Agency (DKPP), has implemented the Agricultural Facilities and Infrastructure Provision and Development Program. This program is designed to strengthen agricultural production capacity by supporting the availability of farming machinery, improving irrigation networks, and developing farm access roads. Despite its strategic importance, the program’s implementation continues to encounter various obstacles, including constrained budget availability, unequal distribution of agricultural facilities, reliance on rain-fed irrigation systems, substandard farm road infrastructure, and limited intensity of agricultural extension services. This research aims to examine the implementation of the Agricultural Facilities and Infrastructure Provision and Development Program in Sukodadi Village, Sukodadi District, Lamongan Regency. The study adopts a qualitative descriptive approach, utilizing data collected through in-depth interviews, direct field observations, and document review. Analysis is conducted using the Van Meter and Van Horn policy implementation framework, which emphasizes six key variables: policy standards and objectives, resource adequacy, characteristics of implementing organizations, inter-organizational communication, implementer disposition, and social, economic, and political conditions. The results reveal that although policy standards and objectives are well defined, program execution remains suboptimal due to limited resources and insufficient institutional support at the operational level. Consequently, stronger coordination among implementing actors and improved resource optimization are necessary to achieve more effective and sustainable agricultural development outcomes.  

The BIMP-EAGA Vision 2035 (BEV 2035) marks a significant paradigm shift in border management in Southeast Asia, with a primary focus on integrating a more inclusive, open, harmonized, and resilient system. In this context, sea-based border crossing posts (PLBN) in Indonesia, such as the Sebatik PLBN, the Serasan PLBN, and the Miangas and Marore Border Crossing Stations (BCS), play a strategic role as maritime connectivity nodes connecting Indonesia with neighboring countries. The transformation of these PLBNs faces several challenges, particularly related to the disharmony of CIQS (Customs, Immigration, Quarantine, and Security) regulations between countries, technical obstacles related to non-conventional vessels (NCSS), and inadequate port infrastructure. To overcome these obstacles, strategic measures are needed, such as revising cross-border trade agreements, increasing quarantine capacity and facilities, and strengthening maritime logistics networks between countries. Furthermore, the development of a sustainable blue economy in border areas is crucial to ensure that the PLBN functions not only as an administrative checkpoint but also as a key facilitator in driving economic growth based on maritime resources. Within the framework of the BIMP-EAGA Vision 2035, the Integrated Maritime PLBN is expected to reduce dependence on informal trade and improve the quality of life of border communities by accelerating connectivity, developing the maritime economic sector, and opening international market access for local products. Thus, the PLBN must transform into a catalyst for inclusive and environmentally friendly economic development in Indonesia's border regions.

This community service activity was carried out to overcome the problem of open and uncontrolled internet networks at SMK Islamiyah Serua. This condition poses security risks as well as inefficient bandwidth usage. The solution offered is the implementation of a network gateway system with a user-friendly web-based login portal, so that internet access can be limited only to educators through an authentication mechanism. The implementation method includes needs analysis, system design, implementation using MikroTik RouterOS and HTML/CSS/JavaScript-based web portals, system trials, and socialization to schools. The results showed a significant improvement in network security, bandwidth usage efficiency, and ease of access for teachers. In addition, this activity also increases educators' understanding of the importance of network security in supporting the learning process. The implementation of this system provides sustainable benefits for schools, both from a technical and educational perspective, because it is able to create a safer and more controlled digital environment. Thus, this community service activity not only solves technical problems, but also contributes to improving the quality of educational services at SMK Islamiyah Serua.

Digital transformation has become a strategic necessity for both public and private organizations in improving efficiency, service quality, and competitiveness in the digital era. The success of digital transformation is greatly influenced by the readiness and planning of integrated and sustainable IT infrastructure. This study aims to analyze the role of IT infrastructure planning in supporting the implementation of organizational digital transformation. The method used is a systematic literature review of scientific publications relevant to the topic of IT infrastructure, strategic information system planning, and digital transformation. The review results indicate that IT infrastructure serves as the main foundation of digital transformation, encompassing hardware, software, networks, data centers, information security, and human resources. Poorly planned IT infrastructure has the potential to cause various issues, such as limited technology capacity, digital divides, cybersecurity risks, and investment inefficiencies. Therefore, strategic IT infrastructure planning that aligns with the organization's vision is required, supported by adequate funding, human resource competency development, and adaptive digital leadership to ensure the successful and sustainable implementation of digital transformation.

Information security is an essential aspect of digital communication, particularly in the exchange of text-based messages through open networks. Messages transmitted without protection are vulnerable to interception and unauthorized modification. One classical cryptographic technique that remains relevant as a foundational learning tool is the Caesar Cipher algorithm. This study aims to implement the Caesar Cipher algorithm for message encryption and decryption and to analyze its effectiveness and security level. The research method employed is a descriptive approach through literature review and a case study by applying character-shift techniques to text messages. The results indicate that the Caesar Cipher algorithm successfully transforms plaintext into ciphertext and restores it back to its original form through the decryption process. Although the algorithm is simple and easy to implement, it has significant limitations in terms of security due to its small key space and vulnerability to brute-force attacks. Therefore, Caesar Cipher is not suitable for protecting sensitive data but remains valuable as an introductory model for understanding basic cryptographic concepts.

Perkembangan teknologi informasi meningkatkan kompleksitas ancaman keamanan siber, salah satunya serangan ARP Spoofing. Serangan ini memanipulasi protokol ARP untuk mengakses dan memodifikasi lalu lintas jaringan, sehingga berpotensi menimbulkan Man-In-The-Middle (MITM) dan pencurian data. Penelitian ini bertujuan merancanag dan mengimplementasikan sistem pemantauan keamanan berbasis multi kriteria untuk mendeteksi serangan ARP Spoofing pada jaringan WiFi. Sistem dikembangkan sebagai Intrusion Prevention System (IPS) yang memantau data ARP dan menerapkan aturan deteksi, seperti ketidaksesuaian IP-MAC, perubahan atribut jaringan yang berlebihan, serta anomali jumlah paket. Notifikasi dikirim secara real-time kepada administrator ketika terjadi penyimpangan. Metode penelitian menggunakan pendekatan Research and Devolpment (R&D), meliputi analisis kebutuhan, perancangan algoritma deteksi, dan pengujian sistem. Eksperimen dilakukan untuk menilai efektivitas deteksi serta efesiensi penggunaan memori. Hasil menunjukkan sistem mampu mendeteksi ARP Spoofing dengan tingkat akurasi tinggi dan konsumsi memori yang efisien. Implementasi sistem ini menurunkan risiko MTIM dan pencurian data, sehingga layak diterapkan pada jaringan kampus maupun organisasi. Konstribusi penelitian ini adalah memperluas kajian keamanan jaringan dengan focus pada ARP spoofing, yang sebelumnya kurang mendapat perhatian dibanding DNS spoofing atau brute force attack. Untuk penelitian selanjutnya, integrasi metode berbasis aturan dengan machine learning diharapkan meningkatkan kemampuan sistem dalam menghadapi pola serangan baru yang lebih kompleks.

This study explores the integration of deep learning based approaches in real time video content analysis for intelligent human computer interaction (HCI) in multimedia systems. Traditional video analysis techniques, such as rule-based methods and offline processing, struggle with real time performance and adaptability to complex video data. In contrast, the deep learning model used in this research, particularly Convolutional Neural Networks (CNNs), provides high accuracy in object detection, feature extraction, and real time processing. The integration of CNNs with interactive visualization modules enables dynamic adjustments to video content based on user interactions, ensuring a seamless and engaging user experience. The system was benchmarked in terms of its processing speed, accuracy, and responsiveness, showing significant improvements over traditional approaches in real time video analysis. Moreover, the study demonstrates that combining deep learning with real time visualization enhances the efficiency of interactive multimedia applications, making it suitable for dynamic environments such as surveillance, security monitoring, and interactive media. Despite the system's strong performance, challenges such as computational demands in high-resolution video processing were identified, highlighting the need for further optimization. Future work will focus on optimizing the system for different hardware platforms, incorporating multimodal inputs, and refining deep learning models to address computational bottlenecks. This research contributes to advancing HCI by providing insights into the integration of deep learning for real time video content analysis, which is pivotal for enhancing the interactivity and adaptability of intelligent multimedia systems.

The increasing complexity and scale of modern cybersecurity threats necessitate the development of advanced systems capable of efficiently detecting, analyzing, and mitigating incidents in real time. This paper proposes an automated framework for digital forensics and incident response that leverages big data analytics and real time network traffic profiling. The framework integrates cutting-edge technologies, including Apache Spark for real time data processing and Hadoop for scalable data storage, combined with machine learning models like LSTM and Autoencoders to detect anomalies and threats in network traffic. By automating the process of incident detection and response, this framework significantly reduces the time required to identify threats and improves the accuracy of forensic evidence correlation across heterogeneous network environments. The study highlights the advantages of using machine learning models and big data tools to address the limitations of traditional manual and semi-automated systems, which often struggle to keep pace with large-scale data generation. Testing results demonstrate that the proposed framework can handle large data volumes efficiently, providing real time, actionable insights with significantly reduced response times. Additionally, the framework improves forensic analysis by enabling the correlation of evidence from different devices and protocols, making it more effective than traditional methods in identifying the root cause of security incidents. However, challenges related to data heterogeneity, scalability, and system integration were encountered during testing. The proposed framework holds promise for significantly enhancing the efficiency and effectiveness of cybersecurity operations, with future work focusing on further integration of advanced AI techniques and machine learning models for dynamic and adaptive incident response.

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.