StageGuard: A hierarchical BERT-BiLSTM framework with stage transition anomaly scoring for fraudulent conversation detection
Defense and Security Studies · 05.08.2026 · 7 (2) · 220-236
DOI: 10.37868/dss.v7.id344 ↗Kurz gefasst
Fachartikel in der Zeitschrift Defense and Security Studies, online erschienen am 05.08.2026. Verfasst von Karrar M. Khudhair und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Fraud conducted through chat applications has grown into a serious global threat affecting millions of people each year. Most detection systems still classify each message in isolation rather than reasoning over the conversation as a whole, which limits their ability to recognise the gradual manipulation that characterises social-engineering fraud. This paper presents StageGuard, a hierarchical deep-learning architecture that models the full trajectory of a fraudulent conversation. The framework builds on the Manipulation Stage Progression Model (MSPM), a five-stage taxonomy grounded in Cialdini's principles of psychological influence [4], in which offenders build trust gradually across turns before exploiting it. On this basis we define the Stage Transition Anomaly Score (STAS), a single-valued, human-readable feature that quantifies how abruptly a conversation moves between stages and serves as an interpretable indicator of manipulative intent. BERT-base-uncased encodes each turn, and the resulting turn embeddings are processed by a bidirectional LSTM [6], [19] with Bahdanau attention [7] that captures temporal dependencies across the conversation. The attention context vector is fused with the STAS and urgency features before a multi-layer classifier produces the fraud decision, and training uses a multi-task objective that jointly optimises fraud detection and per-turn stage classification. Under a leakage-free protocol in which messages are partitioned into disjoint train, validation and test pools before conversations are constructed, and on a realistic task in which both classes contain spam so that content alone is insufficient, StageGuard attains an F1-macro of 0.9919 and an ROC-AUC of 0.9998. The hierarchical design substantially outperforms flat baselines that treat the conversation as a single text (F1 up to 0.952); ablation and McNemar tests indicate that STAS does not change accuracy significantly, and its value is instead the per-turn interpretability it provides for human operators. We further report bootstrap confidence intervals, five-fold cross-validation and an external-domain evaluation that exposes a sharp generalisation gap, which we discuss candidly as a limitation.
Zitieren
APA
Khudhair, K. M., & Khudhair, B. M. (2026). StageGuard: A hierarchical BERT-BiLSTM framework with stage transition anomaly scoring for fraudulent conversation detection. Defense and Security Studies, 7(2), 220-236. https://doi.org/10.37868/dss.v7.id344
Vancouver
Khudhair KM, Khudhair BM. StageGuard: A hierarchical BERT-BiLSTM framework with stage transition anomaly scoring for fraudulent conversation detection. Defense and Security Studies. 2026;7(2):220-236. doi:10.37868/dss.v7.id344
BibTeX
@article{Khudhair2026,
author = {Khudhair, Karrar M. and Khudhair, Bareq M.},
title = {StageGuard: A hierarchical BERT-BiLSTM framework with stage transition anomaly scoring for fraudulent conversation detection},
journal = {Defense and Security Studies},
year = {2026},
volume = {7},
number = {2},
pages = {220--236},
doi = {10.37868/dss.v7.id344}
}
EUVIMED