EUVIMEDEUVIMED entdecken
Crossref

P-TIMA: a framework of T witter threat intelligence mining and analysis based on a prompt-learning NER model

Yizhe You, Zhengwei Jiang, Peian Yang, Jun Jiang, Kai Zhang, Xuren Wang, Chenpeng Tu, Huamin Feng

The Computer Journal · 20.12.2024 · 67 (12) · 3221-3238

DOI: 10.1093/comjnl/bxae084 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Computer Journal, online erschienen am 29.09.2024. Verfasst von Yizhe You und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 58 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Open-source information platforms such as Twitter continuously provide the latest threat intelligence, including new vulnerabilities and in-the-wild exploitations of advanced persistent threat (APT) groups. Automated extraction of threat intelligence from Twitter has become crucial for defenders to access up-to-date threat knowledge. However, existing studies mainly rely on supervised learning methods to extract threat intelligence knowledge, such as entities, which require a large amount of annotated data. This paper presents Threat Intelligence Mining and Analysis based on Prompt Learning (P-TIMA), a framework specifically crafted for extracting and analyzing threat intelligence from Twitter. P-TIMA employs our innovative few-shot entity recognition method, SecEntPrompt (SEP), built on prompt learning, to extract vulnerability intelligence from Twitter. Additionally, P-TIMA analyzes and profiles the overarching vulnerability intelligence obtained from Twitter, along with in-the-wild exploitation intelligence of APT groups. The SEP improves the average entity recognition F1 score by 3.62-4.40 compared with the best-performing comparison model and outperforms the method based on the large language model on recognition performance and inference time. To validate our framework, we apply P-TIMA to extract vulnerability-related threat intelligence from real Twitter data. Through case studies, we then analyze trends in vulnerability threats and the exploitation capabilities of APT groups. In conclusion, our framework provides a more efficient and accurate method for extracting threat intelligence from Twitter, enabling defenders to stay up-to-date with the latest threat trends and helping them improve their defense strategies against cyber attacks.

Zitieren

APA

You, Y., Jiang, Z., Yang, P., Jiang, J., Zhang, K., Wang, X., Tu, C., & Feng, H. (2024). P-TIMA: a framework of T witter threat intelligence mining and analysis based on a prompt-learning NER model. The Computer Journal, 67(12), 3221-3238. https://doi.org/10.1093/comjnl/bxae084

Vancouver

You Y, Jiang Z, Yang P, Jiang J, Zhang K, Wang X, et al. P-TIMA: a framework of T witter threat intelligence mining and analysis based on a prompt-learning NER model. The Computer Journal. 2024;67(12):3221-3238. doi:10.1093/comjnl/bxae084

BibTeX
@article{You2024,
  author = {You, Yizhe and Jiang, Zhengwei and Yang, Peian and Jiang, Jun and Zhang, Kai and Wang, Xuren and Tu, Chenpeng and Feng, Huamin},
  title = {P-TIMA: a framework of T witter threat intelligence mining and analysis based on a prompt-learning NER model},
  journal = {The Computer Journal},
  year = {2024},
  volume = {67},
  number = {12},
  pages = {3221--3238},
  doi = {10.1093/comjnl/bxae084}
}
Kostenlos starten →