Journal of Artificial Intelligence Research

ARTIFICIAL INTELLIGENCE IN CYBERSECURITY RISK ANALYSIS ON NATIONAL VITAL INFRASTRUCTURE

Diana Magfiroh — 2025-01-24

The development of digital technology has a significant impact on increasing cybersecurity threats, especially on national vital infrastructure such as the energy, transportation, and health sectors. Cyberattacks targeting these sectors have the potential to disrupt essential public services and threaten national security. Therefore, the use of Artificial Intelligence (AI) in cybersecurity risk analysis is an urgent need. This study aims to examine the effectiveness of AI in detecting and mitigating cyber threats on vital infrastructure. The method used is a mixed methods approach that involves quantitative analysis through questionnaires on the cybersecurity team and network log data analysis using the Isolation Forest and K-Nearest Neighbors algorithms. The results show that the application of AI can increase the speed of detection and effectiveness of threat mitigation, with anomaly detection accuracy reaching 95% and an odds ratio of 2.5 in cyber threat mitigation. These findings underscore that AI has a significant contribution to strengthening cybersecurity resilience on national infrastructure. However, some challenges such as integration with legacy systems and supporting regulatory needs need to be considered for further optimization.

THE EFFECT OF MACHINE LEARNING ALGORITHMS ON HOAX DETECTION ON SOCIAL MEDIA: IMPLICATIONS FOR NATIONAL INFORMATION SECURITY

Mar’atus Solikhah — 2025-01-27

The spread of hoaxes on social media has become a serious threat to national information security, considering the large number of people who depend on social media as a source of information. This misinformation not only has an impact on public perception but also disrupts social and political stability. This study aims to test the effectiveness of machine learning algorithms, especially Natural Language Processing (NLP), Neural Networks, and Decision Tree, in detecting hoaxes on social media and analyzing their implications for national information security. The method used is a quantitative approach with experimental and comparative analysis of the three algorithms. The data was collected through web scraping from social media platforms and analyzed using the Confusion Matrix to assess accuracy, precision, recall, and F1-score. The results showed that NLP had the highest accuracy, reaching 92.7%, followed by Neural Networks with 90.1% and Decision Tree at 86.3%. In addition, the increase in hoax detection is directly proportional to the decrease in security incidents related to disinformation, indicating the important role of machine learning algorithms in maintaining national information stability. These findings support the implementation of hoax detection algorithms as part of a more comprehensive information security policy.

INTEGRATION OF AI IN EDUCATION SYSTEMS: ADDRESSING LEARNING QUALITY GAPS IN REMOTE AREAS

Nurhaliza Nurhaliza — 2025-01-28

The gap in access and quality of education in remote areas is a major challenge for the equitable distribution of education in Indonesia. Uneven technological infrastructure, especially internet access, hinders students in remote areas from getting the same quality of learning as students in urban areas. This study aims to analyze the potential and challenges of artificial intelligence (AI) integration in improving the quality of education in remote areas. Using a qualitative method with a descriptive approach, data were collected through in-depth interviews, field observations, and document analysis from several schools in remote areas. Data analysis was carried out using thematic analysis methods to identify patterns and key findings. The results show that AI has great potential in providing adaptive and personalized learning, despite significant barriers related to infrastructure and policy support. It was also found that effective AI adoption requires government support in the form of inclusive education policies, teacher training, and digital infrastructure improvements. This research recommends a collaborative strategy between the government, the education sector, and the private sector to strengthen the integration of AI as a long-term solution in addressing education gaps in remote areas.

ETHICAL ANALYSIS OF THE USE OF AI IN MEDICAL DATA MANAGEMENT: PRIVACY CHALLENGES IN THE DIGITAL AGE

Rafi Farizki — 2025-01-31

The use of artificial intelligence (AI) in medical data management has improved efficiency and accuracy in healthcare, but it presents significant ethical challenges, especially when it comes to patient privacy. Along with the rapid development of technology, concerns over the security and privacy violations of medical data are increasing, which can impact public trust in AI-based healthcare systems. The study aims to analyze the ethical challenges in the use of AI in medical data and identify strategies to strengthen patient safety and privacy. Using a qualitative method with a case study approach, this study involves in-depth interviews and analysis of policy documents from several health institutions. The results of the study reveal three main themes: (1) ethical challenges related to transparency and patient consent, (2) the risk of medical data leakage due to the lack of AI security standards, and (3) barriers to ethical AI implementation in the health environment, especially in developing countries. The recommendations of this study include the implementation of the latest encryption protocols, increased ethical awareness among medical personnel, and policy transparency to patients. These findings contribute to the development of medical data privacy policies in the digital era, as well as increasing public trust in AI technology in the health sector.

APPLICATION OF AI IN LOGISTICS AND SUPPLY CHAIN OPTIMIZATION FOR LOCAL ECONOMIC DEVELOPMENT: A CASE STUDY IN THE MSME INDUSTRY

Aldo Faisal Umam — 2025-01-25

Artificial intelligence (AI) has become an important innovation in improving logistics and supply chain efficiency in various sectors, including the Micro, Small, and Medium Enterprises (MSMEs) industry. However, many MSMEs still face challenges in implementing AI effectively, such as limited costs, technical knowledge, and technological infrastructure. This research aims to analyze the application of AI in logistics and supply chain optimization, as well as its impact on local economic development. The research method uses a mixed approach, namely thematic analysis on qualitative data to understand the constraints and perceptions of MSME actors and descriptive statistical analysis on quantitative data to measure the impact of AI application on logistics efficiency. The results show that the application of AI is able to improve the efficiency of stock management, optimize delivery routes, and reduce distribution costs by up to 20%. However, implementation cost constraints and limited technology infrastructure are still the main obstacles for MSMEs in utilizing AI optimally. The recommendations of this study include technology subsidies from the government and technical training programs for MSME actors so that they can overcome challenges and utilize AI to support local economic growth.