The escalating sophistication of cyberattacks necessitates automated extraction of machine-readable intelligence from unstructured Cyber Threat Intelligence (CTI). To address the dual challenges of limited standardized datasets and insufficient domain knowledge utilization, we propose CTINER, the first STIX 2.1-aligned dataset with 42,549 annotated entities across 13 cybersecurity-specific types, surpassing existing resources in scale (+51.82% more annotated entities) and vocabulary coverage (+40.39% more words), while ensuring label rationality and consistency. Furthermore, we introduce PROMPT-BART, a novel named entity recognition (NER) model based on the BART generative model. By integrating template prompting and demonstration learning, PROMPT-BART achieves F1 score improvements ranging from 4.26% to 8.3% over conventional deep learning baselines, and outperforms prompt-based learning baselines by 1.31%.
The growing sophistication of cyberattacks underscores the need for the automated extraction of machine-readable intelligence from unstructured Cyber Threat Intelligence (CTI), commonly achieved through Named Entity Recognition (NER). However, existing CTI-oriented NER research faces two major limitations: the scarcity of standardized datasets and the lack of advanced models tailored to domain-specific entities. To address the dataset challenge, we present CTINER, the first STIX 2.1-aligned dataset, comprising 42,549 annotated entities across 13 cybersecurity-specific types. CTINER surpasses existing resources in both scale (+51.82% more annotated entities) and vocabulary coverage (+40.39%), while ensuring label consistency and rationality. To tackle the modeling challenge, we propose PROMPT-BART, a novel NER model built upon the BART generative framework and enhanced through three types of prompt designs. Experimental results show that PROMPT-BART improves F1 scores by 4.26–8.3% over conventional deep learning baselines and outperforms prompt-based baselines by 1.31%.