Sitemap

Mitigating Adversarial Obfuscation in named entity recognition with Robust SecureBERT Finetuning </a> </h2>

Published in

Computers, Materials & Continua 2025

Paper Link

https://www.techscience.com/cmc/online/detail/25248

Submitted Date

2025-09-09

Accepted Date

2025-11-18

Published Date

2026-02-10

Doi URL

https://doi.org/10.32604/cmc.2025.073029

Doi

10.32604/cmc.2025.073029

LLMs, Cybersecurity

Recommended citation:

         @Article{cmc.2025.073029, AUTHOR = {Nouman Ahmad, Changsheng Zhang, Uroosa Sehar}, TITLE = {Mitigating Adversarial Obfuscation in Named Entity Recognition with Robust SecureBERT Finetuning}, JOURNAL = {Computers, Materials \& Continua}, VOLUME = {87}, YEAR = {2025}, NUMBER = {1}, PAGES = {32}, URL = {http://www.techscience.com/cmc/online/detail/25248}, ISSN = {1546-2226}, ABSTRACT = {Although Named Entity Recognition (NER) in cybersecurity has historically concentrated on threat intelligence, vital security data can be found in a variety of sources, such as open-source intelligence and unprocessed tool outputs. When dealing with technical language, the coexistence of structured and unstructured data poses serious issues for traditional BERT-based techniques. We introduce a three-phase approach for improved NER in multi-source cybersecurity data that makes use of large language models (LLMs). To ensure thorough entity coverage, our method starts with an identification module that uses dynamic prompting techniques. To lessen hallucinations, the extraction module uses confidence-based self-assessment and cross-checking using regex validation. The tagging module links to knowledge bases for contextual validation and uses SecureBERT in conjunction with conditional random fields to detect entity boundaries precisely. Our framework creates efficient natural language segments by utilizing decoder-based LLMs with 10B parameters. When compared to baseline SecureBERT implementations, evaluation across four cybersecurity data sources shows notable gains, with a 9.4%–25.21% greater recall and a 6.38%–17.3% better F1-score. Our refined model matches larger models and achieves 2.6%–4.9% better F1-score for technical phrase recognition than the state-of-the-art alternatives Claude 3.5 Sonnet, Llama3-8B, and Mixtral-7B. The three-stage architecture identification-extraction-tagging pipeline tackles important cybersecurity NER issues. Through effective architectures, these developments preserve deployability while setting a new standard for entity extraction in challenging security scenarios. The findings show how specific enhancements in hybrid recognition, validation procedures, and prompt engineering raise NER performance above monolithic LLM approaches in cybersecurity applications, especially for technical entity extraction from heterogeneous sources where conventional techniques fall short. Because of its modular nature, the framework can be upgraded at the component level as new methods are developed.}, DOI = {10.32604/cmc.2025.073029} }