Adaptive Linguistic Prompting (ALP) Enhances Phishing Webpage Detection in Multimodal Large Language Models Article Swipe

PDF

Atharva Bhargude , Ishan Gonehal , Daeung Yoon , Sean O Brien , Kaustubh Vinnakota , Caelán Max Haney , Alejandro Sandoval , Kevin Zhu ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.18653/v1/2025.nlp4pi-1.7

Phishing attacks represent a significant cybersecurity threat, necessitating adaptive detection techniques. This study explores few-shot Adaptive Linguistic Prompting (ALP) in detecting phishing webpages through the multimodal capabilities of state-of-the-art large language models (LLMs) such as GPT-4o and Gemini 1.5 Pro. ALP is a structured semantic reasoning method that guides LLMs to analyze textual deception by breaking down linguistic patterns, detecting urgency cues, and identifying manipulative diction commonly found in phishing content. By integrating textual, visual, and URL-based analysis, we propose a unified model capable of identifying sophisticated phishing attempts. Our experiments demonstrate that ALP significantly enhances phishing detection accuracy by guiding LLMs through structured reasoning and contextual analysis. The findings highlight the potential of ALP-integrated multimodal LLMs to advance phishing detection frameworks, achieving an F1-score of 0.93, surpassing traditional approaches. These results establish a foundation for more robust, interpretable, and adaptive linguistic-based phishing detection systems using LLMs.

Related Topics

Phishing

Computer Science

Artificial Intelligence

Internet

Philosophy

Concepts

Phishing Computer science Natural language processing Artificial intelligence Speech recognition Linguistics World Wide Web The Internet Philosophy

Metadata

Type: article
Language: en
Landing Page: https://doi.org/10.18653/v1/2025.nlp4pi-1.7
PDF: https://aclanthology.org/2025.nlp4pi-1.7.pdf
OA Status: gold
Related Works: 10
OpenAlex ID: https://openalex.org/W4412944296

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4412944296

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.18653/v1/2025.nlp4pi-1.7

Digital Object Identifier
Title: Adaptive Linguistic Prompting (ALP) Enhances Phishing Webpage Detection in Multimodal Large Language Models

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-01-01

Full publication date if available
Authors: Atharva Bhargude, Ishan Gonehal, Daeung Yoon, Sean O Brien, Kaustubh Vinnakota, Caelán Max Haney, Alejandro Sandoval, Kevin Zhu

List of authors in order
Landing page: https://doi.org/10.18653/v1/2025.nlp4pi-1.7

Publisher landing page
PDF URL: https://aclanthology.org/2025.nlp4pi-1.7.pdf

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: gold

Open access status per OpenAlex
OA URL: https://aclanthology.org/2025.nlp4pi-1.7.pdf

Direct OA link when available
Concepts: Phishing, Computer science, Natural language processing, Artificial intelligence, Speech recognition, Linguistics, World Wide Web, The Internet, Philosophy

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4412944296
doi	https://doi.org/10.18653/v1/2025.nlp4pi-1.7
ids.doi	https://doi.org/10.18653/v1/2025.nlp4pi-1.7
ids.openalex	https://openalex.org/W4412944296
fwci	0.0
type	article
title	Adaptive Linguistic Prompting (ALP) Enhances Phishing Webpage Detection in Multimodal Large Language Models
biblio.issue
biblio.volume
biblio.last_page	85
biblio.first_page	77
topics[0].id	https://openalex.org/T11644
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9961000084877014
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1710
topics[0].subfield.display_name	Information Systems
topics[0].display_name	Spam and Phishing Detection
topics[1].id	https://openalex.org/T10664
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9883999824523926
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Sentiment Analysis and Opinion Mining
topics[2].id	https://openalex.org/T11147
topics[2].field.id	https://openalex.org/fields/33
topics[2].field.display_name	Social Sciences
topics[2].score	0.9818999767303467
topics[2].domain.id	https://openalex.org/domains/2
topics[2].domain.display_name	Social Sciences
topics[2].subfield.id	https://openalex.org/subfields/3312
topics[2].subfield.display_name	Sociology and Political Science
topics[2].display_name	Misinformation and Its Impacts
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C83860907
concepts[0].level	3
concepts[0].score	0.7980291247367859
concepts[0].wikidata	https://www.wikidata.org/wiki/Q135005
concepts[0].display_name	Phishing
concepts[1].id	https://openalex.org/C41008148
concepts[1].level	0
concepts[1].score	0.7099869847297668
concepts[1].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[1].display_name	Computer science
concepts[2].id	https://openalex.org/C204321447
concepts[2].level	1
concepts[2].score	0.5539330244064331
concepts[2].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[2].display_name	Natural language processing
concepts[3].id	https://openalex.org/C154945302
concepts[3].level	1
concepts[3].score	0.4570498764514923
concepts[3].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[3].display_name	Artificial intelligence
concepts[4].id	https://openalex.org/C28490314
concepts[4].level	1
concepts[4].score	0.4013667404651642
concepts[4].wikidata	https://www.wikidata.org/wiki/Q189436
concepts[4].display_name	Speech recognition
concepts[5].id	https://openalex.org/C41895202
concepts[5].level	1
concepts[5].score	0.3545563817024231
concepts[5].wikidata	https://www.wikidata.org/wiki/Q8162
concepts[5].display_name	Linguistics
concepts[6].id	https://openalex.org/C136764020
concepts[6].level	1
concepts[6].score	0.28779107332229614
concepts[6].wikidata	https://www.wikidata.org/wiki/Q466
concepts[6].display_name	World Wide Web
concepts[7].id	https://openalex.org/C110875604
concepts[7].level	2
concepts[7].score	0.18395167589187622
concepts[7].wikidata	https://www.wikidata.org/wiki/Q75
concepts[7].display_name	The Internet
concepts[8].id	https://openalex.org/C138885662
concepts[8].level	0
concepts[8].score	0.0
concepts[8].wikidata	https://www.wikidata.org/wiki/Q5891
concepts[8].display_name	Philosophy
keywords[0].id	https://openalex.org/keywords/phishing
keywords[0].score	0.7980291247367859
keywords[0].display_name	Phishing
keywords[1].id	https://openalex.org/keywords/computer-science
keywords[1].score	0.7099869847297668
keywords[1].display_name	Computer science
keywords[2].id	https://openalex.org/keywords/natural-language-processing
keywords[2].score	0.5539330244064331
keywords[2].display_name	Natural language processing
keywords[3].id	https://openalex.org/keywords/artificial-intelligence
keywords[3].score	0.4570498764514923
keywords[3].display_name	Artificial intelligence
keywords[4].id	https://openalex.org/keywords/speech-recognition
keywords[4].score	0.4013667404651642
keywords[4].display_name	Speech recognition
keywords[5].id	https://openalex.org/keywords/linguistics
keywords[5].score	0.3545563817024231
keywords[5].display_name	Linguistics
keywords[6].id	https://openalex.org/keywords/world-wide-web
keywords[6].score	0.28779107332229614
keywords[6].display_name	World Wide Web
keywords[7].id	https://openalex.org/keywords/the-internet
keywords[7].score	0.18395167589187622
keywords[7].display_name	The Internet
language	en
locations[0].id	doi:10.18653/v1/2025.nlp4pi-1.7
locations[0].is_oa	True
locations[0].source
locations[0].license	cc-by
locations[0].pdf_url	https://aclanthology.org/2025.nlp4pi-1.7.pdf
locations[0].version	publishedVersion
locations[0].raw_type	proceedings-article
locations[0].license_id	https://openalex.org/licenses/cc-by
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	Proceedings of the Fourth Workshop on NLP for Positive Impact (NLP4PI)
locations[0].landing_page_url	https://doi.org/10.18653/v1/2025.nlp4pi-1.7
locations[1].id	pmh:oai:arXiv.org:2507.13357
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url	https://arxiv.org/pdf/2507.13357
locations[1].version	submittedVersion
locations[1].raw_type	text
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published	False
locations[1].raw_source_name
locations[1].landing_page_url	http://arxiv.org/abs/2507.13357
indexed_in	arxiv, crossref
authorships[0].author.id	https://openalex.org/A5119204192
authorships[0].author.orcid
authorships[0].author.display_name	Atharva Bhargude
authorships[0].author_position	first
authorships[0].raw_author_name	Atharva Bhargude
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5119204193
authorships[1].author.orcid
authorships[1].author.display_name	Ishan Gonehal
authorships[1].author_position	middle
authorships[1].raw_author_name	Ishan Gonehal
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5013644671
authorships[2].author.orcid	https://orcid.org/0000-0003-4715-1853
authorships[2].author.display_name	Daeung Yoon
authorships[2].author_position	middle
authorships[2].raw_author_name	Dave Yoon
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5119204194
authorships[3].author.orcid
authorships[3].author.display_name	Sean O Brien
authorships[3].author_position	middle
authorships[3].raw_author_name	Sean O Brien
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5119204195
authorships[4].author.orcid
authorships[4].author.display_name	Kaustubh Vinnakota
authorships[4].author_position	middle
authorships[4].raw_author_name	Kaustubh Vinnakota
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5090494918
authorships[5].author.orcid	https://orcid.org/0000-0002-4209-9470
authorships[5].author.display_name	Caelán Max Haney
authorships[5].author_position	middle
authorships[5].raw_author_name	Chandler Haney
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5005440935
authorships[6].author.orcid	https://orcid.org/0000-0002-8558-6033
authorships[6].author.display_name	Alejandro Sandoval
authorships[6].author_position	middle
authorships[6].raw_author_name	Aaron Sandoval
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5101471343
authorships[7].author.orcid	https://orcid.org/0009-0008-1881-8384
authorships[7].author.display_name	Kevin Zhu
authorships[7].author_position	last
authorships[7].raw_author_name	Kevin Zhu
authorships[7].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://aclanthology.org/2025.nlp4pi-1.7.pdf
open_access.oa_status	gold
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Adaptive Linguistic Prompting (ALP) Enhances Phishing Webpage Detection in Multimodal Large Language Models
has_fulltext	True
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic.id	https://openalex.org/T11644
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9961000084877014
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1710
primary_topic.subfield.display_name	Information Systems
primary_topic.display_name	Spam and Phishing Detection
related_works	https://openalex.org/W2149202530, https://openalex.org/W2807822918, https://openalex.org/W2921723332, https://openalex.org/W4391093354, https://openalex.org/W2482950156, https://openalex.org/W4396966040, https://openalex.org/W2305322260, https://openalex.org/W3139248031, https://openalex.org/W3042334625, https://openalex.org/W3204019825
cited_by_count	0
locations_count	2
best_oa_location.id	doi:10.18653/v1/2025.nlp4pi-1.7
best_oa_location.is_oa	True
best_oa_location.source
best_oa_location.license	cc-by
best_oa_location.pdf_url	https://aclanthology.org/2025.nlp4pi-1.7.pdf
best_oa_location.version	publishedVersion
best_oa_location.raw_type	proceedings-article
best_oa_location.license_id	https://openalex.org/licenses/cc-by
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	Proceedings of the Fourth Workshop on NLP for Positive Impact (NLP4PI)
best_oa_location.landing_page_url	https://doi.org/10.18653/v1/2025.nlp4pi-1.7
primary_location.id	doi:10.18653/v1/2025.nlp4pi-1.7
primary_location.is_oa	True
primary_location.source
primary_location.license	cc-by
primary_location.pdf_url	https://aclanthology.org/2025.nlp4pi-1.7.pdf
primary_location.version	publishedVersion
primary_location.raw_type	proceedings-article
primary_location.license_id	https://openalex.org/licenses/cc-by
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	Proceedings of the Fourth Workshop on NLP for Positive Impact (NLP4PI)
primary_location.landing_page_url	https://doi.org/10.18653/v1/2025.nlp4pi-1.7
publication_date	2025-01-01
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	3, 42, 80, 133
abstract_inverted_index.By	71
abstract_inverted_index.an	123
abstract_inverted_index.as	34
abstract_inverted_index.by	54, 99
abstract_inverted_index.in	19, 68
abstract_inverted_index.is	41
abstract_inverted_index.of	27, 84, 113, 125
abstract_inverted_index.to	50, 117
abstract_inverted_index.we	78
abstract_inverted_index.1.5	38
abstract_inverted_index.ALP	40, 93
abstract_inverted_index.Our	89
abstract_inverted_index.The	108
abstract_inverted_index.and	36, 62, 75, 105, 139
abstract_inverted_index.for	135
abstract_inverted_index.the	24, 111
abstract_inverted_index.LLMs	49, 101, 116
abstract_inverted_index.Pro.	39
abstract_inverted_index.This	11
abstract_inverted_index.down	56
abstract_inverted_index.more	136
abstract_inverted_index.such	33
abstract_inverted_index.that	47, 92
abstract_inverted_index.(ALP)	18
abstract_inverted_index.0.93,	126
abstract_inverted_index.LLMs.	146
abstract_inverted_index.These	130
abstract_inverted_index.cues,	61
abstract_inverted_index.found	67
abstract_inverted_index.large	29
abstract_inverted_index.model	82
abstract_inverted_index.study	12
abstract_inverted_index.using	145
abstract_inverted_index.(LLMs)	32
abstract_inverted_index.GPT-4o	35
abstract_inverted_index.Gemini	37
abstract_inverted_index.guides	48
abstract_inverted_index.method	46
abstract_inverted_index.models	31
abstract_inverted_index.advance	118
abstract_inverted_index.analyze	51
abstract_inverted_index.attacks	1
abstract_inverted_index.capable	83
abstract_inverted_index.diction	65
abstract_inverted_index.guiding	100
abstract_inverted_index.propose	79
abstract_inverted_index.results	131
abstract_inverted_index.robust,	137
abstract_inverted_index.systems	144
abstract_inverted_index.textual	52
abstract_inverted_index.threat,	6
abstract_inverted_index.through	23, 102
abstract_inverted_index.unified	81
abstract_inverted_index.urgency	60
abstract_inverted_index.visual,	74
abstract_inverted_index.Adaptive	15
abstract_inverted_index.F1-score	124
abstract_inverted_index.Phishing	0
abstract_inverted_index.accuracy	98
abstract_inverted_index.adaptive	8, 140
abstract_inverted_index.breaking	55
abstract_inverted_index.commonly	66
abstract_inverted_index.content.	70
abstract_inverted_index.enhances	95
abstract_inverted_index.explores	13
abstract_inverted_index.few-shot	14
abstract_inverted_index.findings	109
abstract_inverted_index.language	30
abstract_inverted_index.phishing	21, 69, 87, 96, 119, 142
abstract_inverted_index.semantic	44
abstract_inverted_index.textual,	73
abstract_inverted_index.webpages	22
abstract_inverted_index.Prompting	17
abstract_inverted_index.URL-based	76
abstract_inverted_index.achieving	122
abstract_inverted_index.analysis,	77
abstract_inverted_index.analysis.	107
abstract_inverted_index.attempts.	88
abstract_inverted_index.deception	53
abstract_inverted_index.detecting	20, 59
abstract_inverted_index.detection	9, 97, 120, 143
abstract_inverted_index.establish	132
abstract_inverted_index.highlight	110
abstract_inverted_index.patterns,	58
abstract_inverted_index.potential	112
abstract_inverted_index.reasoning	45, 104
abstract_inverted_index.represent	2
abstract_inverted_index.Linguistic	16
abstract_inverted_index.contextual	106
abstract_inverted_index.foundation	134
abstract_inverted_index.linguistic	57
abstract_inverted_index.multimodal	25, 115
abstract_inverted_index.structured	43, 103
abstract_inverted_index.surpassing	127
abstract_inverted_index.approaches.	129
abstract_inverted_index.demonstrate	91
abstract_inverted_index.experiments	90
abstract_inverted_index.frameworks,	121
abstract_inverted_index.identifying	63, 85
abstract_inverted_index.integrating	72
abstract_inverted_index.significant	4
abstract_inverted_index.techniques.	10
abstract_inverted_index.traditional	128
abstract_inverted_index.capabilities	26
abstract_inverted_index.manipulative	64
abstract_inverted_index.cybersecurity	5
abstract_inverted_index.necessitating	7
abstract_inverted_index.significantly	94
abstract_inverted_index.sophisticated	86
abstract_inverted_index.ALP-integrated	114
abstract_inverted_index.interpretable,	138
abstract_inverted_index.linguistic-based	141
abstract_inverted_index.state-of-the-art	28
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	8
citation_normalized_percentile.value	0.43478082
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	True