Research on named entity recognition method in cybersecurity based on soft prompt tuning and reinforcement learning
As network technology rapidly advanced, new cybersecurity threats constantly emerged, increasing the importance of cybersecurity named entity recognition. To address the problem of poor recognition accuracy in named entity recognition methods based on large language models in the cybersecurity domai...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2024-10-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024183/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841537123257155584 |
|---|---|
| author | TIAN Zeshu LIU Chunyu ZHANG Yunting ZHANG Jiayu MENG Chao ZHANG Hongli |
| author_facet | TIAN Zeshu LIU Chunyu ZHANG Yunting ZHANG Jiayu MENG Chao ZHANG Hongli |
| author_sort | TIAN Zeshu |
| collection | DOAJ |
| description | As network technology rapidly advanced, new cybersecurity threats constantly emerged, increasing the importance of cybersecurity named entity recognition. To address the problem of poor recognition accuracy in named entity recognition methods based on large language models in the cybersecurity domain, a novel cybersecurity named entity recognition method that combined soft prompt tuning and reinforcement learning was proposed. By integrating the soft prompt tuning technique, the method precisely adjusted the recognition capabilities of large language models to handle the complexity of the cybersecurity domain, improving recognition accuracy for cybersecurity named entities while optimizing training efficiency. Additionally, a reinforcement learning-based instance filter was proposed, which effectively removed low-quality annotations from the training set, further enhancing recognition accuracy. The proposed method was evaluated on two benchmark cybersecurity NER datasets, with experimental results demonstrating superior performance in F1 score compared to state-of-the-art cybersecurity NER methods. |
| format | Article |
| id | doaj-art-98eee83559904de8b653a2cbb26ad1c4 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2024-10-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-98eee83559904de8b653a2cbb26ad1c42025-01-14T08:46:07ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2024-10-014511677077797Research on named entity recognition method in cybersecurity based on soft prompt tuning and reinforcement learningTIAN ZeshuLIU ChunyuZHANG YuntingZHANG JiayuMENG ChaoZHANG HongliAs network technology rapidly advanced, new cybersecurity threats constantly emerged, increasing the importance of cybersecurity named entity recognition. To address the problem of poor recognition accuracy in named entity recognition methods based on large language models in the cybersecurity domain, a novel cybersecurity named entity recognition method that combined soft prompt tuning and reinforcement learning was proposed. By integrating the soft prompt tuning technique, the method precisely adjusted the recognition capabilities of large language models to handle the complexity of the cybersecurity domain, improving recognition accuracy for cybersecurity named entities while optimizing training efficiency. Additionally, a reinforcement learning-based instance filter was proposed, which effectively removed low-quality annotations from the training set, further enhancing recognition accuracy. The proposed method was evaluated on two benchmark cybersecurity NER datasets, with experimental results demonstrating superior performance in F1 score compared to state-of-the-art cybersecurity NER methods.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024183/cybersecurity named entity recognitionsoft prompt tuningreinforcement learninglarge-scale pre-trained models |
| spellingShingle | TIAN Zeshu LIU Chunyu ZHANG Yunting ZHANG Jiayu MENG Chao ZHANG Hongli Research on named entity recognition method in cybersecurity based on soft prompt tuning and reinforcement learning Tongxin xuebao cybersecurity named entity recognition soft prompt tuning reinforcement learning large-scale pre-trained models |
| title | Research on named entity recognition method in cybersecurity based on soft prompt tuning and reinforcement learning |
| title_full | Research on named entity recognition method in cybersecurity based on soft prompt tuning and reinforcement learning |
| title_fullStr | Research on named entity recognition method in cybersecurity based on soft prompt tuning and reinforcement learning |
| title_full_unstemmed | Research on named entity recognition method in cybersecurity based on soft prompt tuning and reinforcement learning |
| title_short | Research on named entity recognition method in cybersecurity based on soft prompt tuning and reinforcement learning |
| title_sort | research on named entity recognition method in cybersecurity based on soft prompt tuning and reinforcement learning |
| topic | cybersecurity named entity recognition soft prompt tuning reinforcement learning large-scale pre-trained models |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024183/ |
| work_keys_str_mv | AT tianzeshu researchonnamedentityrecognitionmethodincybersecuritybasedonsoftprompttuningandreinforcementlearning AT liuchunyu researchonnamedentityrecognitionmethodincybersecuritybasedonsoftprompttuningandreinforcementlearning AT zhangyunting researchonnamedentityrecognitionmethodincybersecuritybasedonsoftprompttuningandreinforcementlearning AT zhangjiayu researchonnamedentityrecognitionmethodincybersecuritybasedonsoftprompttuningandreinforcementlearning AT mengchao researchonnamedentityrecognitionmethodincybersecuritybasedonsoftprompttuningandreinforcementlearning AT zhanghongli researchonnamedentityrecognitionmethodincybersecuritybasedonsoftprompttuningandreinforcementlearning |