In the dynamic intersection of Natural Language Processing~(NLP) and cyber security, Named Entity Recognition~(NER) plays a pivotal role in comprehending and countering cyber threats. This paper explores NER techniques within the cyber security context, utilizing a meticulously curated dataset with 12 distinct entity types extracted from security blogs. Our study involves developing and comparative analysis of five NER models: BiLSTM, BiLSTM-CRF, BERT, BERT-CRF, and BERT-BiLSTM-CRF. Rigorous evaluation reveals that the BERT-BiLSTM-CRF model outperforms others with an F1-Score of 0.9635, excelling at extracting entities from the intricate language used in cyber security texts. Through this paper, we contribute to the ongoing NER discourse in cyber security, paving the way for advancements in NLP techniques and fortifying cyber security measures against evolving digital threats.
If you find our work helpful, please consider citing our paper:
@inproceedings{aravind2023cytie, title={CyTIE: Cyber Threat Intelligence Extraction with Named Entity Recognition}, author={Aravind, PC and Arikkat, Dincy R and Krishnan, Anupama S and Tesneem, Bahja and Sebastian, Aparna and Dev, Mridul J and Aswathy, KR and Rehiman, KA Rafidha and Vinod, P}, booktitle={International Conference on Advancements in Smart Computing and Information Security}, pages={163--178}, year={2023}, organization={Springer} }