ENIXMA: ENsemble of EXplainable Methods for Detecting Network Attacks

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

Abtahi Seyed Mojtaba; RAHMANI HOSSEIN; Allahgholi Milad; Alizade Sajjad

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Seminar Paper

Paper Information

Seminar: INTERNATIONAL CONFERENCE ON WEB RESEARCH
Year:2023 | Issue:9

Download Full-Text

View:

Download:

Information Seminar Paper

Title

ENIXMA: ENsemble of EXplainable Methods for Detecting Network Attacks

Author(s)

Abtahi Seyed Mojtaba | RAHMANI HOSSEIN | Allahgholi Milad | Alizade Sajjad

Keywords

Anomaly detection

machine learning

network data

botnet

data mining

ensemble learning

interpretability

Abstract

Today, the Internet is a major part of society. Given the ubiquity of the Internet, its availability is a must. Attackers, on the other hand, seek to make Internet services inaccessible and exploit Internet service companies. Attackers use various tools and methods to attack the networks and infrastructure of service companies. These attacks are also called network traffic anomalies. In general, malfunctions or attacks are network events that deviate from normal expected behavior and are suspicious of security. In general, anomalies or attacks are network events that deviate from expected normal behavior and are suspicious from a security point of view. Many different methods have been proposed to detect attacks in the network. One of the most important challenges of the previous methods is the low accuracy and lack of interpretability. In this paper, we tried to use a combination of basic methods to detect attacks and achieve 89% attack detection accuracy in the balanced dataset. This accuracy has increased by 3% compared to previous works. In order to solve the challenge of interpretability, we applied SHAP, LIME and decision tree methods and identified the effective features in detecting attacks. The proposed method, in addition to high accuracy and interpretability, has a higher speed than previous works.

Cites

No record.

References

No record.

Cite

APA: Copy

Abtahi, Seyed Mojtaba, RAHMANI, HOSSEIN, Allahgholi, Milad, & Alizade, Sajjad. (). . . SID. https://sid.ir/paper/1047261/en

Vancouver: Copy

Abtahi Seyed Mojtaba, RAHMANI HOSSEIN, Allahgholi Milad, Alizade Sajjad. . . Available from: https://sid.ir/paper/1047261/en

IEEE: Copy

Seyed Mojtaba Abtahi, HOSSEIN RAHMANI, Milad Allahgholi, and Sajjad Alizade, “,” presented at the . , [Online]. Available: https://sid.ir/paper/1047261/en

Related Journal Papers

No record.

Related Seminar Papers

No record.

Related Plans

No record.

Recommended Workshops