Hybrid CNN-GRU Framework with Integrated Pre-trained Language Transformer for SMS Phishing Detection

Rubaiath E. Ulfath; Hamed Alqahtani; Mohammad Hammoudeh; Iqbal H. Sarker

doi:10.1145/3508072.3508109

Hybrid CNN-GRU Framework with Integrated Pre-trained Language Transformer for SMS Phishing Detection

Rubaiath E. Ulfath, Hamed Alqahtani, Mohammad Hammoudeh, Iqbal H. Sarker

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

11 Scopus citations

Abstract

Smartphones are prone to SMS phishing due to the rapid growth in the availability of smart mobile technologies driven by Internet connections. Also, detecting phishing SMS is a challenging task due to the unstructured nature of SMS text data with non-linear complex correlations. In this concern, considering the recent advancements in the domain of cybersecurity, we have proposed a hybrid deep learning framework that extracts robust features from SMS texts followed by an automatic detection of Phishing SMS. Due to combining the potential capability of individual models into one hybrid framework, it has outperformed various other individual machine learning and deep learning models. The proposed Phishing Detection framework is an effective hybrid combination of pretrained transformer model, MPNet (Masked and Permuted Language Modeling), with supervised ConvNets (CNN) and Bi-directional Gated Recurrent Units (GRU). It is intended to successfully detect unstructured short phishing text messages that contain complex patterns.

Original language	English
Title of host publication	ICFNDS 2021 - 5th International Conference on Future Networks and Distributed Systems
Subtitle of host publication	The Premier Conference on Smart Next Generation Networking Technologies
Publisher	Association for Computing Machinery
Pages	244-251
Number of pages	8
ISBN (Electronic)	9781450387347
DOIs	https://doi.org/10.1145/3508072.3508109
State	Published - 15 Dec 2021
Externally published	Yes

Publication series

Name	ACM International Conference Proceeding Series

Bibliographical note

Publisher Copyright:
© 2021 ACM.

Keywords

AI
Cybersecurity
Deep learning
NLP
Smishing

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/3508072.3508109

Cite this

Ulfath, R. E., Alqahtani, H., Hammoudeh, M., & Sarker, I. H. (2021). Hybrid CNN-GRU Framework with Integrated Pre-trained Language Transformer for SMS Phishing Detection. In ICFNDS 2021 - 5th International Conference on Future Networks and Distributed Systems: The Premier Conference on Smart Next Generation Networking Technologies (pp. 244-251). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3508072.3508109

Ulfath, Rubaiath E. ; Alqahtani, Hamed ; Hammoudeh, Mohammad et al. / Hybrid CNN-GRU Framework with Integrated Pre-trained Language Transformer for SMS Phishing Detection. ICFNDS 2021 - 5th International Conference on Future Networks and Distributed Systems: The Premier Conference on Smart Next Generation Networking Technologies. Association for Computing Machinery, 2021. pp. 244-251 (ACM International Conference Proceeding Series).

@inproceedings{da88e0469246447fa268aab6baa798df,

title = "Hybrid CNN-GRU Framework with Integrated Pre-trained Language Transformer for SMS Phishing Detection",

abstract = "Smartphones are prone to SMS phishing due to the rapid growth in the availability of smart mobile technologies driven by Internet connections. Also, detecting phishing SMS is a challenging task due to the unstructured nature of SMS text data with non-linear complex correlations. In this concern, considering the recent advancements in the domain of cybersecurity, we have proposed a hybrid deep learning framework that extracts robust features from SMS texts followed by an automatic detection of Phishing SMS. Due to combining the potential capability of individual models into one hybrid framework, it has outperformed various other individual machine learning and deep learning models. The proposed Phishing Detection framework is an effective hybrid combination of pretrained transformer model, MPNet (Masked and Permuted Language Modeling), with supervised ConvNets (CNN) and Bi-directional Gated Recurrent Units (GRU). It is intended to successfully detect unstructured short phishing text messages that contain complex patterns.",

keywords = "AI, Cybersecurity, Deep learning, NLP, Smishing",

author = "Ulfath, \{Rubaiath E.\} and Hamed Alqahtani and Mohammad Hammoudeh and Sarker, \{Iqbal H.\}",

note = "Publisher Copyright: {\textcopyright} 2021 ACM.",

year = "2021",

month = dec,

day = "15",

doi = "10.1145/3508072.3508109",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "244--251",

booktitle = "ICFNDS 2021 - 5th International Conference on Future Networks and Distributed Systems",

}

Ulfath, RE, Alqahtani, H, Hammoudeh, M & Sarker, IH 2021, Hybrid CNN-GRU Framework with Integrated Pre-trained Language Transformer for SMS Phishing Detection. in ICFNDS 2021 - 5th International Conference on Future Networks and Distributed Systems: The Premier Conference on Smart Next Generation Networking Technologies. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 244-251. https://doi.org/10.1145/3508072.3508109

Hybrid CNN-GRU Framework with Integrated Pre-trained Language Transformer for SMS Phishing Detection. / Ulfath, Rubaiath E.; Alqahtani, Hamed; Hammoudeh, Mohammad et al.
ICFNDS 2021 - 5th International Conference on Future Networks and Distributed Systems: The Premier Conference on Smart Next Generation Networking Technologies. Association for Computing Machinery, 2021. p. 244-251 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - Hybrid CNN-GRU Framework with Integrated Pre-trained Language Transformer for SMS Phishing Detection

AU - Ulfath, Rubaiath E.

AU - Alqahtani, Hamed

AU - Hammoudeh, Mohammad

AU - Sarker, Iqbal H.

PY - 2021/12/15

Y1 - 2021/12/15

N2 - Smartphones are prone to SMS phishing due to the rapid growth in the availability of smart mobile technologies driven by Internet connections. Also, detecting phishing SMS is a challenging task due to the unstructured nature of SMS text data with non-linear complex correlations. In this concern, considering the recent advancements in the domain of cybersecurity, we have proposed a hybrid deep learning framework that extracts robust features from SMS texts followed by an automatic detection of Phishing SMS. Due to combining the potential capability of individual models into one hybrid framework, it has outperformed various other individual machine learning and deep learning models. The proposed Phishing Detection framework is an effective hybrid combination of pretrained transformer model, MPNet (Masked and Permuted Language Modeling), with supervised ConvNets (CNN) and Bi-directional Gated Recurrent Units (GRU). It is intended to successfully detect unstructured short phishing text messages that contain complex patterns.

AB - Smartphones are prone to SMS phishing due to the rapid growth in the availability of smart mobile technologies driven by Internet connections. Also, detecting phishing SMS is a challenging task due to the unstructured nature of SMS text data with non-linear complex correlations. In this concern, considering the recent advancements in the domain of cybersecurity, we have proposed a hybrid deep learning framework that extracts robust features from SMS texts followed by an automatic detection of Phishing SMS. Due to combining the potential capability of individual models into one hybrid framework, it has outperformed various other individual machine learning and deep learning models. The proposed Phishing Detection framework is an effective hybrid combination of pretrained transformer model, MPNet (Masked and Permuted Language Modeling), with supervised ConvNets (CNN) and Bi-directional Gated Recurrent Units (GRU). It is intended to successfully detect unstructured short phishing text messages that contain complex patterns.

KW - AI

KW - Cybersecurity

KW - Deep learning

KW - NLP

KW - Smishing

UR - https://www.scopus.com/pages/publications/85128659734

U2 - 10.1145/3508072.3508109

DO - 10.1145/3508072.3508109

M3 - Conference contribution

AN - SCOPUS:85128659734

T3 - ACM International Conference Proceeding Series

SP - 244

EP - 251

BT - ICFNDS 2021 - 5th International Conference on Future Networks and Distributed Systems

PB - Association for Computing Machinery

ER -

Ulfath RE, Alqahtani H, Hammoudeh M, Sarker IH. Hybrid CNN-GRU Framework with Integrated Pre-trained Language Transformer for SMS Phishing Detection. In ICFNDS 2021 - 5th International Conference on Future Networks and Distributed Systems: The Premier Conference on Smart Next Generation Networking Technologies. Association for Computing Machinery. 2021. p. 244-251. (ACM International Conference Proceeding Series). doi: 10.1145/3508072.3508109

Hybrid CNN-GRU Framework with Integrated Pre-trained Language Transformer for SMS Phishing Detection

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this