Publisher

Tel-UTel-U

Journal International Journal on Information and Communication Technology (IJoICT)International Journal on Information and Communication Technology (IJoICT) Abstract

This research focuses on the problem identification of common cyber threats, particularly viruses, using sentiment analysis based on machine learning. The challenge of analyzing unstructured data, such as articles and technical reports, to identify and categorize cybercrime attacks. The novelty of this research is creating a trend dashboard about news trends using a Cyber Threat Intelligence (CTI) engine approach to identify cyber threats. This research method uses cosine similarity to search for news articles by matching them to cybercrime incidents that frequently occur and leverage AI techniques such as TF-IDF and Bag of Words to extract relevant information from CTI documents. Our study highlights the importance of this approach in improving cybersecurity. The findings of this research are that there is an increasing trend in news of cybercrime incidents in Indonesia with the type of Trojan virus with a cosine similarity of 73.41 according to data processing using the BSSN (National Cyber and Crypto Agency) table in Indonesia from 2019 to 2021, frequent incidents were found appears in the type of virus trojan-downloader: win32small and heur:trojan win32.generik.

Conclusion

The research findings indicate a rising trend in cybercrime incident reports within Indonesia, particularly pertaining to Trojan viruses.The most frequently occurring incidents are Trojan threats with a cosine similarity of 73.41, identified through data processed using the BSSN table from 2019 to 2021.This study emphasizes the importance of preventative measures against viruses and cybercrimes to enhance cybersecurity in Indonesia.

Future Research

Further research should investigate the application of more advanced machine learning models, such as deep learning, to improve the accuracy and efficiency of cyber threat detection from unstructured data sources. Additionally, exploring the integration of diverse data sources, including dark web forums and social media platforms, could provide a more comprehensive view of emerging cyber threats and attacker tactics. Finally, a study focusing on the development of automated response mechanisms based on identified threats, leveraging the MITRE ATT&CK framework, would be valuable in enhancing proactive cybersecurity defenses and reducing the impact of cyberattacks. These investigations will contribute to a more robust and adaptive cybersecurity ecosystem, enabling organizations and individuals to better protect themselves against the evolving landscape of cybercrime, and will build upon the current researchs focus on Indonesian cyber threats by expanding the scope to include a broader range of attack vectors and mitigation strategies, ultimately fostering a more secure digital environment.

References

1. Machine Learning Sentiment Analysis in Cyber Threat Intelligence Recommendation System | International... doi.org/10.21108/ijoict.v9i2.849Machine Learning Sentiment Analysis in Cyber Threat Intelligence Recommendation System International doi 10 21108 ijoict v9i2 849

Metadata

File size	422.95 KB
Pages	11
DMCA	Report