CoChat

Optimising Insider Threat Prediction: Exploring BiLSTM Networks and Sequential Features

Open access
Manoharan, Phavithra, Hong, Wei, Yin, Jiao, Wang, Hua, Zhang, Yanchun, Ye, Wenjie · 2024 · Data Science and Engineering

The DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index.

Abstract

Abstract Insider threats pose a critical risk to organisations, impacting their data, processes, resources, and overall security. Such significant risks arise from individuals with authorised access and familiarity with internal systems, emphasising the potential for insider threats to compromise the integrity of organisations. Previous research has addressed the challenge by pinpointing malicious actions that have already occurred but provided limited assistance in preventing those risks. In this research, we introduce a novel approach based on bidirectional long short-term memory (BiLSTM) networks that effectively captures and analyses the patterns of individual actions and their sequential dependencies. The focus is on predicting whether an individual would be a malicious insider in a future day based on their daily behavioural records over the previous several days. We analyse the performance of the four supervised learning algorithms on manual features, sequential features, and the ground truth of the day with different combinations. In addition, we investigate the performance of different RNN models, such as RNN, LSTM, and BiLSTM, in incorporating these features. Moreover, we explore the performance of different predictive lengths on the ground truth of the day and different embedded lengths for the sequential features. All the experiments are conducted on the CERT r4.2 dataset. Experiment results show that BiLSTM has the highest performance in combining these features.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s41019-024-00260-z

Cites

56 of 56 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Prediction Framework
Fig. 1 Prediction FrameworkCC-BY · From the PDF
Fig. 2 Performance of various features on supervised learning algorithms
Fig. 2 Performance of various features on supervised learning algorithmsCC-BY · From the PDF
Fig. 3 Performance of various sequential models on Xm ‖ Xs ‖ Xg
Fig. 3 Performance of various sequential models on Xm ‖ Xs ‖ XgCC-BY · From the PDF
Image 4
CC-BY · From the PDF
Fig. 5 F1 score for various embeded_size on BiLSTM
Fig. 5 F1 score for various embeded_size on BiLSTMCC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 6

  1. Sun X, Li M, Wang H, Plank A (2008) An efficient hash-based algorithm for minimal k-anonymity. In: Conferences in research and practice in information technology (CRPIT), vol 74, Austral- ian Computer Society Inc, pp 101-107
  2. Huang T, Gong Y, Kwong S, Wang H, Zhang J (2019) A niching memetic algorithm for multi-solution traveling salesman problem. IEEE Trans Evol Comput 24(3):508-522
  3. Brackney RC, Anderson RH (2004) Understanding the insider threat. Proceedings of a march 2004 workshop. Technical report, RAND CORP SANTA MONICA CA 40. Lütkebohle I (2023) Cybersecurity and infrastructure security agency(CISA). https:// www. cisa. gov/ defin ing-insid er-threa ts. Accessed 20 Ju 2023
  4. Tuor A, Kaplan S, Hutchinson B, Nichols N, Robinson S (2017) Deep learning for unsupervised insider threat detection in struc- tured cybersecurity data streams. arXiv preprint arXiv: 1710. 00811 (2017)
  5. Medsker LR, Jain L et al (2001) Recurrent neural networks. Des Appl 5(64-67):2
  6. Pascanu R Mikolov T, Bengio Y (2013) On the difficulty of train- ing recurrent neural networks. In: International conference on machine learning, Pmlr, pp 1310-1318

Cited by

See all 28

Metadata

Authors
Manoharan, P., Hong, W., Yin, J., Wang, H., Zhang, Y., & Ye, W.
Affiliations
  • Victoria University (AU)
  • La Trobe University (AU)
  • Zhejiang Normal University (CN)
Corresponding author
Yin, Jiao
Venue
Data Science and Engineering
Published
2024-11-21
Volume
9
Issue
4
Pages
393-408
ISSN
  • 2364-1185 (ISSN-L)
  • 2364-1541
OpenAlex
W4404606174
Cited by
22
References
56
Citations by year
2026: 17 · 2025: 5
FWCI
8.27
Type
journal article
Language
en
Open access
Licence
Locations
  • Data Science and Engineering (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Information Systems › Information and Cyber Security
  • Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
Keywords
bidirectional LSTM, user behavior analysis, recurrent neural networks, supervised learning, insider threat prevention

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.