<![CDATA[With the rapid advancement of digital technology, the threat of malware has become increasingly prevalent and sophisticated, posing significant risks to both individuals and organizations. Despite the growing need for robust protection, many existing malware analysis tools are overly complex, often requiring advanced technical knowledge, which makes them less accessible to general users. To address this gap, this study proposes the development of a web-based malware analysis system that is both powerful and user-friendly. The system is built using the Streamlit framework, which allows for the creation of interactive and responsive web applications with minimal overhead. At its core, the system integrates a Machine Learning model based on the Random Forest algorithm, chosen for its high accuracy and robustness in classification tasks, particularly in distinguishing between benign and malicious files. For in-depth file analysis, the system connects to the MetaDefender API, which scans submitted files using multiple antivirus engines and provides comprehensive threat intelligence data. To further enhance accessibility, especially for users without a technical background, the GPT API is integrated to automatically generate simplified interpretations of complex scan results, explaining the findings in natural language. The system displays results using graphical visualizations, making it easier for users to comprehend potential threats without needing to interpret raw data or technical jargon. This visual and interactive approach supports real-time decision-making and improves user experience. The methodology employed in this research is quantitative, focusing on the evaluation of the system’s performance and the effectiveness of the Random Forest model in accurately classifying malware. Key performance metrics such as accuracy, precision, recall, and F1-score are used in the analysis. Overall, this system offers several competitive advantages: enhanced accessibility, improved ease of use, and simplified result interpretation compared to traditional malware analysis tools. The research contributes to the broader field of cybersecurity by providing a more practical and user-friendly solution for malware detection, thereby helping to raise awareness and improve protective measures against digital threats.]]>
Copyrights © 2025
