As cyberattacks grow increasingly sophisticated, advanced Network Intrusion Detection Systems (NIDS) have become essential for securing cyberspace. While Machine Learning (ML) is foundational to modern NIDS, its effectiveness is often hampered by a resource-intensive development pipeline involving feature engineering, model selection, and hyperparameter tuning. Automated Machine Learning (AutoML) promises a solution, but its application to the massive, high-speed data streams in NIDS is fundamentally a parallel and distributed computing challenge. This paper argues that the scalability and performance of AutoML in NIDS are governed by the underlying computational paradigm. We introduce a novel taxonomy of AutoML frameworks, uniquely classifying them by their parallel and distributed architectures. Through a comprehensive meta-analysis of over 15 NID methods on benchmark datasets, we demonstrate how the performance of leading systems is a direct consequence of their chosen computational paradigm. Finally, we identify frontier challenges and future research directions at the intersection of AutoML, NIDS, and high-performance distributed systems, focusing on computational scalability, security, and end-to-end automation.
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%.