SpamLLM: Leveraging Large Language Models for Robust Spam Email Classification.
Saved in:
| Title: | SpamLLM: Leveraging Large Language Models for Robust Spam Email Classification. |
|---|---|
| Authors: | He, Zhiyong1 (AUTHOR) 2012100740@niit.edu.cn, Liu, Chang2 (AUTHOR), Hu, Boyang3 (AUTHOR), Jia, Duo4 (AUTHOR), Murray, Richard (AUTHOR) rmurray@wiley.com |
| Source: | International Journal of Intelligent Systems. 6/23/2026, Vol. 2026, p1-17. 17p. |
| Subjects: | Spam filtering (Email), Language models, Spam email, Latent semantic analysis, Email security, Transformer models, Machine learning |
| Abstract: | Spam email detection remains an ongoing challenge due to the increasing sophistication and evolving tactics employed by spammers. Traditional rule–based and machine learning (ML) detection methods have demonstrated limitations in adaptability and generalization. This paper proposes SpamLLM, a multimodal spam detection framework that leverages a frozen large language model (LLM) backbone integrated with semantic embeddings and structured metadata extracted from email headers and body statistics. Rigorous evaluations are conducted across four widely used spam detection datasets, and SpamLLM is compared against classical ML, deep learning, and pretrained Transformer‐based baseline models. The experimental results demonstrate that SpamLLM outperforms existing methods and achieves state‐of‐the‐art performance in accuracy, precision, recall, and F1 score. Notably, SpamLLM excels in handling diverse spam content and provides robust detection across various datasets. These findings underscore the potential of multimodal fusion approaches for advancing spam classification systems and suggest promising directions for future research in email security. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Intelligent Systems is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 194784057 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: SpamLLM: Leveraging Large Language Models for Robust Spam Email Classification. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22He%2C+Zhiyong%22">He, Zhiyong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> 2012100740@niit.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Liu%2C+Chang%22">Liu, Chang</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hu%2C+Boyang%22">Hu, Boyang</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Jia%2C+Duo%22">Jia, Duo</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Murray%2C+Richard%22">Murray, Richard</searchLink> (AUTHOR)<i> rmurray@wiley.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Intelligent+Systems%22">International Journal of Intelligent Systems</searchLink>. 6/23/2026, Vol. 2026, p1-17. 17p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Spam+filtering+%28Email%29%22">Spam filtering (Email)</searchLink><br /><searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink><br /><searchLink fieldCode="DE" term="%22Spam+email%22">Spam email</searchLink><br /><searchLink fieldCode="DE" term="%22Latent+semantic+analysis%22">Latent semantic analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Email+security%22">Email security</searchLink><br /><searchLink fieldCode="DE" term="%22Transformer+models%22">Transformer models</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Spam email detection remains an ongoing challenge due to the increasing sophistication and evolving tactics employed by spammers. Traditional rule–based and machine learning (ML) detection methods have demonstrated limitations in adaptability and generalization. This paper proposes SpamLLM, a multimodal spam detection framework that leverages a frozen large language model (LLM) backbone integrated with semantic embeddings and structured metadata extracted from email headers and body statistics. Rigorous evaluations are conducted across four widely used spam detection datasets, and SpamLLM is compared against classical ML, deep learning, and pretrained Transformer‐based baseline models. The experimental results demonstrate that SpamLLM outperforms existing methods and achieves state‐of‐the‐art performance in accuracy, precision, recall, and F1 score. Notably, SpamLLM excels in handling diverse spam content and provides robust detection across various datasets. These findings underscore the potential of multimodal fusion approaches for advancing spam classification systems and suggest promising directions for future research in email security. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of International Journal of Intelligent Systems is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194784057 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1155/int/2309553 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 17 StartPage: 1 Subjects: – SubjectFull: Spam filtering (Email) Type: general – SubjectFull: Language models Type: general – SubjectFull: Spam email Type: general – SubjectFull: Latent semantic analysis Type: general – SubjectFull: Email security Type: general – SubjectFull: Transformer models Type: general – SubjectFull: Machine learning Type: general Titles: – TitleFull: SpamLLM: Leveraging Large Language Models for Robust Spam Email Classification. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: He, Zhiyong – PersonEntity: Name: NameFull: Liu, Chang – PersonEntity: Name: NameFull: Hu, Boyang – PersonEntity: Name: NameFull: Jia, Duo – PersonEntity: Name: NameFull: Murray, Richard IsPartOfRelationships: – BibEntity: Dates: – D: 23 M: 06 Text: 6/23/2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 08848173 Numbering: – Type: volume Value: 2026 Titles: – TitleFull: International Journal of Intelligent Systems Type: main |
| ResultId | 1 |
