A Web Attack Detection Method Based on DistilBERT and Feature Fusion for Power Micro-Application Server

Li Nige; Chen Lu; Zhao Lei; Teng Zhenning; Wang Zhiqiang; Shao Yiyang; Gui Xiaolin

doi:10.1109/AEEGE58828.2023.00010

A Web Attack Detection Method Based on DistilBERT and Feature Fusion for Power Micro-Application Server

Li Nige
, Chen Lu
, Zhao Lei
, Teng Zhenning
, Wang Zhiqiang
, Shao Yiyang
, Gui Xiaolin

Faculty of Electronic and Information Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

The widespread use of power micro-applications has significantly expanded the attack surface of their server side, thus increasing the risk of vulnerability attacks such as SQL injection, XSS, and CRLF injection. To ensure the security of power systems, these attacks must be detected precisely and timely. Therefore, this paper proposes a server-side web attack detection method based on DistilBERT and feature fusion for HTTP and HTTPS requests. The method treats HTTP and HTTPS requests as text data, specifically, extracts deep semantic features using DistilBERT, and fuses them with well-designed empirical features to comprehensively characterize and classify the request. Consequently, anomalous requests can be detected. The experimental results show that the accuracy, precision, recall, and F1 score of the method on HTTP CSIC 2010 and FWAF datasets are close to or higher than 99%. Compared with other methods as far as we known, this method has better performance and efficiency.

Original language	English
Title of host publication	Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	6-12
Number of pages	7
ISBN (Electronic)	9798350322866
DOIs	https://doi.org/10.1109/AEEGE58828.2023.00010
State	Published - 2023
Event	2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023 - Singapore, Singapore Duration: 26 May 2023 → 28 May 2023

Publication series

Name	Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023

Conference

Conference	2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023
Country/Territory	Singapore
City	Singapore
Period	26/05/23 → 28/05/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

DistilBERT
cybersecurity
feature fusion
power micro-service
web attack detection

Access to Document

10.1109/AEEGE58828.2023.00010

Cite this

Nige, L., Lu, C., Lei, Z., Zhenning, T., Zhiqiang, W., Yiyang, S., & Xiaolin, G. (2023). A Web Attack Detection Method Based on DistilBERT and Feature Fusion for Power Micro-Application Server. In Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023 (pp. 6-12). (Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AEEGE58828.2023.00010

Nige, Li ; Lu, Chen ; Lei, Zhao et al. / A Web Attack Detection Method Based on DistilBERT and Feature Fusion for Power Micro-Application Server. Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 6-12 (Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023).

@inproceedings{7651419640b34b7a8bf12b359d8dc147,

title = "A Web Attack Detection Method Based on DistilBERT and Feature Fusion for Power Micro-Application Server",

abstract = "The widespread use of power micro-applications has significantly expanded the attack surface of their server side, thus increasing the risk of vulnerability attacks such as SQL injection, XSS, and CRLF injection. To ensure the security of power systems, these attacks must be detected precisely and timely. Therefore, this paper proposes a server-side web attack detection method based on DistilBERT and feature fusion for HTTP and HTTPS requests. The method treats HTTP and HTTPS requests as text data, specifically, extracts deep semantic features using DistilBERT, and fuses them with well-designed empirical features to comprehensively characterize and classify the request. Consequently, anomalous requests can be detected. The experimental results show that the accuracy, precision, recall, and F1 score of the method on HTTP CSIC 2010 and FWAF datasets are close to or higher than 99\%. Compared with other methods as far as we known, this method has better performance and efficiency.",

keywords = "DistilBERT, cybersecurity, feature fusion, power micro-service, web attack detection",

author = "Li Nige and Chen Lu and Zhao Lei and Teng Zhenning and Wang Zhiqiang and Shao Yiyang and Gui Xiaolin",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023 ; Conference date: 26-05-2023 Through 28-05-2023",

year = "2023",

doi = "10.1109/AEEGE58828.2023.00010",

language = "英语",

series = "Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "6--12",

booktitle = "Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023",

}

Nige, L, Lu, C, Lei, Z, Zhenning, T, Zhiqiang, W, Yiyang, S & Xiaolin, G 2023, A Web Attack Detection Method Based on DistilBERT and Feature Fusion for Power Micro-Application Server. in Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023. Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023, Institute of Electrical and Electronics Engineers Inc., pp. 6-12, 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023, Singapore, Singapore, 26/05/23. https://doi.org/10.1109/AEEGE58828.2023.00010

A Web Attack Detection Method Based on DistilBERT and Feature Fusion for Power Micro-Application Server. / Nige, Li; Lu, Chen; Lei, Zhao et al.
Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 6-12 (Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Web Attack Detection Method Based on DistilBERT and Feature Fusion for Power Micro-Application Server

AU - Nige, Li

AU - Lu, Chen

AU - Lei, Zhao

AU - Zhenning, Teng

AU - Zhiqiang, Wang

AU - Yiyang, Shao

AU - Xiaolin, Gui

PY - 2023

Y1 - 2023

N2 - The widespread use of power micro-applications has significantly expanded the attack surface of their server side, thus increasing the risk of vulnerability attacks such as SQL injection, XSS, and CRLF injection. To ensure the security of power systems, these attacks must be detected precisely and timely. Therefore, this paper proposes a server-side web attack detection method based on DistilBERT and feature fusion for HTTP and HTTPS requests. The method treats HTTP and HTTPS requests as text data, specifically, extracts deep semantic features using DistilBERT, and fuses them with well-designed empirical features to comprehensively characterize and classify the request. Consequently, anomalous requests can be detected. The experimental results show that the accuracy, precision, recall, and F1 score of the method on HTTP CSIC 2010 and FWAF datasets are close to or higher than 99%. Compared with other methods as far as we known, this method has better performance and efficiency.

AB - The widespread use of power micro-applications has significantly expanded the attack surface of their server side, thus increasing the risk of vulnerability attacks such as SQL injection, XSS, and CRLF injection. To ensure the security of power systems, these attacks must be detected precisely and timely. Therefore, this paper proposes a server-side web attack detection method based on DistilBERT and feature fusion for HTTP and HTTPS requests. The method treats HTTP and HTTPS requests as text data, specifically, extracts deep semantic features using DistilBERT, and fuses them with well-designed empirical features to comprehensively characterize and classify the request. Consequently, anomalous requests can be detected. The experimental results show that the accuracy, precision, recall, and F1 score of the method on HTTP CSIC 2010 and FWAF datasets are close to or higher than 99%. Compared with other methods as far as we known, this method has better performance and efficiency.

KW - DistilBERT

KW - cybersecurity

KW - feature fusion

KW - power micro-service

KW - web attack detection

UR - https://www.scopus.com/pages/publications/85179519703

U2 - 10.1109/AEEGE58828.2023.00010

DO - 10.1109/AEEGE58828.2023.00010

M3 - 会议稿件

AN - SCOPUS:85179519703

T3 - Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023

SP - 6

EP - 12

BT - Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023

Y2 - 26 May 2023 through 28 May 2023

ER -

Nige L, Lu C, Lei Z, Zhenning T, Zhiqiang W, Yiyang S et al. A Web Attack Detection Method Based on DistilBERT and Feature Fusion for Power Micro-Application Server. In Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 6-12. (Proceedings - 2023 2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023). doi: 10.1109/AEEGE58828.2023.00010

A Web Attack Detection Method Based on DistilBERT and Feature Fusion for Power Micro-Application Server

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this