PhishGNN: A Phishing Website Detection Framework using Graph Neural Networks

Tristan Bilot; Grégoire Geis; Badis Hammi

doi:10.5220/0011328600003283

PhishGNN: A Phishing Website Detection Framework using Graph Neural Networks

Tristan Bilot, Grégoire Geis, Badis Hammi

EPITA

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

Abstract

Because of the importance of the web in our daily lives, phishing attacks have been causing a significant damage to both individuals and organizations. Indeed, phishing attacks are today among the most widespread and serious threats to the web and its users. Currently, the main approaches deployed against such attacks are blacklists. However, the latter represent numerous drawbacks. In this paper, we introduce PhishGNN, a Deep Learning framework based on Graph Neural Networks, which leverages and uses the hyperlink graph structure of websites along with different other hand-designed features. The performance results obtained, demonstrate that PhishGNN outperforms state of the art results with a 99.7% prediction accuracy.

Original language	English
Title of host publication	SECRYPT 2022 - Proceedings of the 19th International Conference on Security and Cryptography
Editors	Sabrina De Capitani di Vimercati, Pierangela Samarati
Publisher	Science and Technology Publications, Lda
Pages	428-435
Number of pages	8
ISBN (Print)	9789897585906
DOIs	https://doi.org/10.5220/0011328600003283
Publication status	Published - 1 Jan 2022
Externally published	Yes
Event	19th International Conference on Security and Cryptography, SECRYPT 2022 - Lisbon, Portugal Duration: 11 Jul 2022 → 13 Jul 2022

Publication series

Name	Proceedings of the International Conference on Security and Cryptography
Volume	1
ISSN (Print)	2184-7711

Conference

Conference	19th International Conference on Security and Cryptography, SECRYPT 2022
Country/Territory	Portugal
City	Lisbon
Period	11/07/22 → 13/07/22

Keywords

Cybersecurity
Deep Learning
Graph Neural Networks
Phishing Detection

Access to Document

10.5220/0011328600003283

Cite this

Bilot, T., Geis, G., & Hammi, B. (2022). PhishGNN: A Phishing Website Detection Framework using Graph Neural Networks. In S. De Capitani di Vimercati, & P. Samarati (Eds.), SECRYPT 2022 - Proceedings of the 19th International Conference on Security and Cryptography (pp. 428-435). (Proceedings of the International Conference on Security and Cryptography; Vol. 1). Science and Technology Publications, Lda. https://doi.org/10.5220/0011328600003283

Bilot, Tristan ; Geis, Grégoire ; Hammi, Badis. / PhishGNN : A Phishing Website Detection Framework using Graph Neural Networks. SECRYPT 2022 - Proceedings of the 19th International Conference on Security and Cryptography. editor / Sabrina De Capitani di Vimercati ; Pierangela Samarati. Science and Technology Publications, Lda, 2022. pp. 428-435 (Proceedings of the International Conference on Security and Cryptography).

@inproceedings{ed1a19c87f6142dfaf265a6b6c6cb704,

title = "PhishGNN: A Phishing Website Detection Framework using Graph Neural Networks",

abstract = "Because of the importance of the web in our daily lives, phishing attacks have been causing a significant damage to both individuals and organizations. Indeed, phishing attacks are today among the most widespread and serious threats to the web and its users. Currently, the main approaches deployed against such attacks are blacklists. However, the latter represent numerous drawbacks. In this paper, we introduce PhishGNN, a Deep Learning framework based on Graph Neural Networks, which leverages and uses the hyperlink graph structure of websites along with different other hand-designed features. The performance results obtained, demonstrate that PhishGNN outperforms state of the art results with a 99.7\% prediction accuracy.",

keywords = "Cybersecurity, Deep Learning, Graph Neural Networks, Phishing Detection",

author = "Tristan Bilot and Gr{\'e}goire Geis and Badis Hammi",

note = "Publisher Copyright: {\textcopyright} 2021 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved.; 19th International Conference on Security and Cryptography, SECRYPT 2022 ; Conference date: 11-07-2022 Through 13-07-2022",

year = "2022",

month = jan,

day = "1",

doi = "10.5220/0011328600003283",

language = "English",

isbn = "9789897585906",

series = "Proceedings of the International Conference on Security and Cryptography",

publisher = "Science and Technology Publications, Lda",

pages = "428--435",

editor = "\{De Capitani di Vimercati\}, Sabrina and Pierangela Samarati",

booktitle = "SECRYPT 2022 - Proceedings of the 19th International Conference on Security and Cryptography",

}

Bilot, T, Geis, G & Hammi, B 2022, PhishGNN: A Phishing Website Detection Framework using Graph Neural Networks. in S De Capitani di Vimercati & P Samarati (eds), SECRYPT 2022 - Proceedings of the 19th International Conference on Security and Cryptography. Proceedings of the International Conference on Security and Cryptography, vol. 1, Science and Technology Publications, Lda, pp. 428-435, 19th International Conference on Security and Cryptography, SECRYPT 2022, Lisbon, Portugal, 11/07/22. https://doi.org/10.5220/0011328600003283

PhishGNN: A Phishing Website Detection Framework using Graph Neural Networks. / Bilot, Tristan; Geis, Grégoire; Hammi, Badis.
SECRYPT 2022 - Proceedings of the 19th International Conference on Security and Cryptography. ed. / Sabrina De Capitani di Vimercati; Pierangela Samarati. Science and Technology Publications, Lda, 2022. p. 428-435 (Proceedings of the International Conference on Security and Cryptography; Vol. 1).

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

TY - GEN

T1 - PhishGNN

T2 - 19th International Conference on Security and Cryptography, SECRYPT 2022

AU - Bilot, Tristan

AU - Geis, Grégoire

AU - Hammi, Badis

PY - 2022/1/1

Y1 - 2022/1/1

N2 - Because of the importance of the web in our daily lives, phishing attacks have been causing a significant damage to both individuals and organizations. Indeed, phishing attacks are today among the most widespread and serious threats to the web and its users. Currently, the main approaches deployed against such attacks are blacklists. However, the latter represent numerous drawbacks. In this paper, we introduce PhishGNN, a Deep Learning framework based on Graph Neural Networks, which leverages and uses the hyperlink graph structure of websites along with different other hand-designed features. The performance results obtained, demonstrate that PhishGNN outperforms state of the art results with a 99.7% prediction accuracy.

AB - Because of the importance of the web in our daily lives, phishing attacks have been causing a significant damage to both individuals and organizations. Indeed, phishing attacks are today among the most widespread and serious threats to the web and its users. Currently, the main approaches deployed against such attacks are blacklists. However, the latter represent numerous drawbacks. In this paper, we introduce PhishGNN, a Deep Learning framework based on Graph Neural Networks, which leverages and uses the hyperlink graph structure of websites along with different other hand-designed features. The performance results obtained, demonstrate that PhishGNN outperforms state of the art results with a 99.7% prediction accuracy.

KW - Cybersecurity

KW - Deep Learning

KW - Graph Neural Networks

KW - Phishing Detection

U2 - 10.5220/0011328600003283

DO - 10.5220/0011328600003283

M3 - Conference contribution

AN - SCOPUS:85147984209

SN - 9789897585906

T3 - Proceedings of the International Conference on Security and Cryptography

SP - 428

EP - 435

BT - SECRYPT 2022 - Proceedings of the 19th International Conference on Security and Cryptography

A2 - De Capitani di Vimercati, Sabrina

A2 - Samarati, Pierangela

PB - Science and Technology Publications, Lda

Y2 - 11 July 2022 through 13 July 2022

ER -

Bilot T, Geis G, Hammi B. PhishGNN: A Phishing Website Detection Framework using Graph Neural Networks. In De Capitani di Vimercati S, Samarati P, editors, SECRYPT 2022 - Proceedings of the 19th International Conference on Security and Cryptography. Science and Technology Publications, Lda. 2022. p. 428-435. (Proceedings of the International Conference on Security and Cryptography). doi: 10.5220/0011328600003283

PhishGNN: A Phishing Website Detection Framework using Graph Neural Networks

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this