Insight-LLM: LLM-enhanced Multi-view Fusion in Insider Threat Detection Article Swipe

PDF

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2509.01509

Insider threat detection (ITD) requires analyzing sparse, heterogeneous user behavior. Existing ITD methods predominantly rely on single-view modeling, resulting in limited coverage and missed anomalies. While multi-view learning has shown promise in other domains, its direct application to ITD introduces significant challenges: scalability bottlenecks from independently trained sub-models, semantic misalignment across disparate feature spaces, and view imbalance that causes high-signal modalities to overshadow weaker ones. In this work, we present Insight-LLM, the first modular multi-view fusion framework specifically tailored for insider threat detection. Insight-LLM employs frozen, pre-nes, achieving state-of-the-art detection with low latency and parameter overhead.

Related Topics

Truth And Reconciliation Commission Of Canada

Alanis Morissette

2025 Nba Draft

28 Years Later

Reich Ministry Of Public Enlightenment And Propaganda

Mahmood Mamdani

Rick Hurst

Mutual Aid

Degenerate Art Exhibition

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2509.01509
PDF: https://arxiv.org/pdf/2509.01509
OA Status: green
OpenAlex ID: https://openalex.org/W4416694288

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416694288

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2509.01509

Digital Object Identifier
Title: Insight-LLM: LLM-enhanced Multi-view Fusion in Insider Threat Detection

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-09-01

Full publication date if available
Authors: Chengyu Song, Jianming Zheng

List of authors in order
Landing page: https://arxiv.org/abs/2509.01509

Publisher landing page
PDF URL: https://arxiv.org/pdf/2509.01509

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2509.01509

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416694288
doi	https://doi.org/10.48550/arxiv.2509.01509
ids.doi	https://doi.org/10.48550/arxiv.2509.01509
ids.openalex	https://openalex.org/W4416694288
fwci
type	preprint
title	Insight-LLM: LLM-enhanced Multi-view Fusion in Insider Threat Detection
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2509.01509
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2509.01509
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2509.01509
locations[1].id	doi:10.48550/arxiv.2509.01509
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
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2509.01509
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5032690266
authorships[0].author.orcid	https://orcid.org/0000-0001-7020-7603
authorships[0].author.display_name	Chengyu Song
authorships[0].author_position	first
authorships[0].raw_author_name	Song, Chengyu
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5023144456
authorships[1].author.orcid	https://orcid.org/0000-0002-4928-8194
authorships[1].author.display_name	Jianming Zheng
authorships[1].author_position	last
authorships[1].raw_author_name	Zheng, Jianming
authorships[1].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2509.01509
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Insight-LLM: LLM-enhanced Multi-view Fusion in Insider Threat Detection
has_fulltext	False
is_retracted	False
updated_date	2025-11-28T20:50:16.243143
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2509.01509
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2509.01509
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2509.01509
primary_location.id	pmh:oai:arXiv.org:2509.01509
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2509.01509
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2509.01509
publication_date	2025-09-01
publication_year	2025
referenced_works_count	0
abstract_inverted_index.In	65
abstract_inverted_index.in	19, 31
abstract_inverted_index.on	15
abstract_inverted_index.to	37, 61
abstract_inverted_index.we	68
abstract_inverted_index.ITD	11, 38
abstract_inverted_index.and	22, 54, 93
abstract_inverted_index.for	79
abstract_inverted_index.has	28
abstract_inverted_index.its	34
abstract_inverted_index.low	91
abstract_inverted_index.the	71
abstract_inverted_index.from	44
abstract_inverted_index.rely	14
abstract_inverted_index.that	57
abstract_inverted_index.this	66
abstract_inverted_index.user	8
abstract_inverted_index.view	55
abstract_inverted_index.with	90
abstract_inverted_index.(ITD)	3
abstract_inverted_index.While	25
abstract_inverted_index.first	72
abstract_inverted_index.ones.	64
abstract_inverted_index.other	32
abstract_inverted_index.shown	29
abstract_inverted_index.work,	67
abstract_inverted_index.across	50
abstract_inverted_index.causes	58
abstract_inverted_index.direct	35
abstract_inverted_index.fusion	75
abstract_inverted_index.missed	23
abstract_inverted_index.threat	1, 81
abstract_inverted_index.weaker	63
abstract_inverted_index.Insider	0
abstract_inverted_index.employs	84
abstract_inverted_index.feature	52
abstract_inverted_index.frozen,	85
abstract_inverted_index.insider	80
abstract_inverted_index.latency	92
abstract_inverted_index.limited	20
abstract_inverted_index.methods	12
abstract_inverted_index.modular	73
abstract_inverted_index.present	69
abstract_inverted_index.promise	30
abstract_inverted_index.spaces,	53
abstract_inverted_index.sparse,	6
abstract_inverted_index.trained	46
abstract_inverted_index.Existing	10
abstract_inverted_index.coverage	21
abstract_inverted_index.domains,	33
abstract_inverted_index.learning	27
abstract_inverted_index.pre-nes,	86
abstract_inverted_index.requires	4
abstract_inverted_index.semantic	48
abstract_inverted_index.tailored	78
abstract_inverted_index.achieving	87
abstract_inverted_index.analyzing	5
abstract_inverted_index.behavior.	9
abstract_inverted_index.detection	2, 89
abstract_inverted_index.disparate	51
abstract_inverted_index.framework	76
abstract_inverted_index.imbalance	56
abstract_inverted_index.modeling,	17
abstract_inverted_index.overhead.	95
abstract_inverted_index.parameter	94
abstract_inverted_index.resulting	18
abstract_inverted_index.anomalies.	24
abstract_inverted_index.detection.	82
abstract_inverted_index.introduces	39
abstract_inverted_index.modalities	60
abstract_inverted_index.multi-view	26, 74
abstract_inverted_index.overshadow	62
abstract_inverted_index.Insight-LLM	83
abstract_inverted_index.application	36
abstract_inverted_index.bottlenecks	43
abstract_inverted_index.challenges:	41
abstract_inverted_index.high-signal	59
abstract_inverted_index.scalability	42
abstract_inverted_index.significant	40
abstract_inverted_index.single-view	16
abstract_inverted_index.sub-models,	47
abstract_inverted_index.Insight-LLM,	70
abstract_inverted_index.misalignment	49
abstract_inverted_index.specifically	77
abstract_inverted_index.heterogeneous	7
abstract_inverted_index.independently	45
abstract_inverted_index.predominantly	13
abstract_inverted_index.state-of-the-art	88
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	2
citation_normalized_percentile