CoChat
Sign Up
PreprintCited by 102Spam and Phishing DetectionHate Speech and Cyberbullying DetectionMisinformation and Its Impacts

The DOI matches its Crossref record; 30 of the 32 references it cites were found in a registry or an index.

An Improved Transformer-based Model for Detecting Phishing, Spam, and Ham: A Large Language Model Approach

Open access
Jamal, Suhaima, Wimmer, Hayden, Sarker, Iqbal·2023·Research Square
DOI 10.21203/rs.3.rs-3608294/v1
Open this paper in CoChat — free accountOpen PDF

Abstract

Phishing and spam detection is a long standing challenge that has been the subject of much academic research. Large Language Models (LLM) have vast potential to transform society and provide new and innovative approaches to solve well-established challenges. Phishing and spam have caused financial hardships and lost time and resources to email users all over the world and frequently serve as an entry point for ransomware threat actors. While detection approaches exist, especially heuristic-based approaches, LLMs offer the potential to venture into a new unexplored area for understanding and solving this challenge. LLMs have rapidly altered the landscape from business, consumers, and throughout academia and demonstrate transformational potential for the potential of society. Based on this, applying these new and innovative approaches to email detection is a rational next step in academic research. In this work, we present IPSDM, an improved phishing spam detection model based on fine-tuning the BERT family of models to specifically detect phishing and spam email. We demonstrate our fine-tuned version, IPSDM, is able to better classify emails in both unbalanced and balanced datasets.

Overview

Integrity signals

Registry

Crossref · 10.21203/rs.3.rs-3608294/v1

Cites

30 of 30 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 32 references

Research works printed but not linked: 5

  1. Araci, Dogu (2019) Finbert: Financial sentiment analysis with pre-trained language models. arXiv preprint arXiv:1908.10063 · arXiv
  2. Manaa, Mehdi and Obaid, Ahmed and Dosh, Mohammed (2021) Unsupervised approach for email spam filtering using data mining. EAI Endorsed Transactions on Energy Web 8(36)
  3. Le, Hung and Pham, Quang and Sahoo, Doyen and Hoi, Steven CH (2018) URLNet: Learning a URL representation with deep learning for malicious URL detection. arXiv preprint arXiv:1802.03162 · arXiv
  4. Sanh, Victor and Debut, Lysandre and Chaumond, Julien and Wolf, Thomas (2019) DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 · arXiv
  5. Zhuang, Zhenxun and Liu, Mingrui and Cutkosky, Ashok and Orabona, Francesco (2022) Understanding adamw through proximal methods and scale-freeness. arXiv preprint arXiv:2202.00089 · arXiv

Cited by

Sorted by citations

Related

See all

Metadata

Authors
Jamal, S., Wimmer, H., & Sarker, I.
Affiliations
  • Georgia Southern University (US)
  • Edith Cowan University (AU)
ORCID
Venue
Research Square
Publisher
Research Square Platform LLC
Published
2023-12-01
DOI
10.21203/rs.3.rs-3608294/v1
OpenAlex
W4389245454
Cited by
27
References
32
Citations by year
2026: 3 · 2025: 16 · 2024: 7 · 2023: 1
Type
posted content
Language
en
Open access
Licence
Locations
  • Research Square (acceptedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Topics
  • Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
  • Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
Keywords
phishing detection, email spam detection, large language models, BERT fine-tuning, email classification, class imbalance

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review