AI-DRIVEN STATISTICAL ANALYSIS FOR CRIMINOLOGICAL CYBERSECURITY: MITIGATING WORKPLACE HARASSMENT AGAINST SINGLE WOMEN IN ENTERPRISE NETWORKS
DOI:
https://doi.org/10.71146/kjmr983Keywords:
Cyber security, criminology, women, work placeAbstract
The intersection of criminology, social dynamics, and enterprise cybersecurity represents a critical frontier in modern organizational management. As the digital workplace expands, malicious insider activities have evolved beyond traditional data theft to encompass interpersonal cyberstalking and workplace harassment, disproportionately affecting vulnerable demographics such as single women. This paper proposes a novel, interdisciplinary framework that leverages artificial intelligence and statistical analysis to detect and mitigate these highly specific behavioral anomalies within enterprise networks. By integrating advanced feature selection techniques, neurosymbolic artificial intelligence, and interpretable machine learning models, the proposed system translates criminological indicators of harassment into measurable network traffic anomalies. Furthermore, we discuss the practical implications of deploying such systems in small and medium-sized enterprises, alongside the ethical complexities of monitoring employee behavior. Ultimately, this research bridges the gap between technical intrusion detection systems and human-centric criminological analysis, offering a foundational blueprint for protecting targeted individuals in hyper-connected organizational environments.
Downloads
References
Kumar, Prabhat, & Islam, A. K. M. Najmul (2024). Interpretable Cyber Threat Detection for Enterprise Industrial Networks: A Computational Design Science Approach. https://arxiv.org/pdf/2409.03798v1
Abie, Habtamu, & Pirbhulal, Sandeep (2024). Autonomous Adaptive Security Framework for 5G-Enabled IoT. https://arxiv.org/pdf/2406.03186v1
Tran, Huynh T. T., Sander, Jacob, Cohen, Achraf, Jalaian, Brian, & Bastian, Nathaniel D. (2025). Neurosymbolic AI Transfer Learning Improves Network Intrusion Detection. https://arxiv.org/pdf/2509.10850v1
Assen, Jan von der, Celdrán, Alberto Huertas, Luechinger, Janik, Sánchez, Pedro Miguel Sánchez, Bovet, Gérôme, Pérez, Gregorio Martínez, & Stiller, Burkhard (2023). RansomAI: AI-powered Ransom ware for Stealthy Encryption. https://arxiv.org/pdf/2306.15559v1
Quayyum, Farzana, Bueie, Jonas, Cruzes, Daniela S., Jaccheri, Letizia, & Vidal, Juan Carlos Torrado (2021). Understanding parents' perceptions of children's cybersecurity awareness in Norway. https://arxiv.org/pdf/2108.02512v1
Shojaifar, Alireza, Fricker, Samuel A., & Gwerder, Martin (2020). Elicitation of SME Requirements for Cybersecurity Solutions by Studying Adherence to Recommendations. https://arxiv.org/pdf/2007.08177v1
Silva, Miguel, Vitorino, João, Maia, Eva, & Praça, Isabel (2024). Efficient Network Traffic Feature Sets for IoT Intrusion Detection. https://arxiv.org/pdf/2406.08042v1
Laprade, Craig, Bowman, Benjamin, & Huang, H. Howie (2020). PicoDomain: A Compact High-Fidelity Cybersecurity Dataset. https://arxiv.org/pdf/2008.09192v1
Ghajari, Ghazal, Ghimire, Ashutosh, Ghajari, Elaheh, & Amsaad, Fathi (2025). Network Anomaly Detection for IoT Using Hyper dimensional Computing on NSL-KDD. https://doi.org/10.1109/SATC65530.2025.11136944
Abreu, Diego, Rothenberg, Christian Esteve, & Abelem, Antonio (2024). QML-IDS: Quantum Machine Learning Intrusion Detection System. https://doi.org/10.1109/ISCC61673.2024.10733655
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 Dr Anum Ali, Zaheema Iqbal (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
KJMR publishes all articles as open access under CC BY 4.0, allowing anyone to share and adapt the work, even commercially, with proper credit, a license link, and clear notice of changes, without implying endorsement. Authors retain copyright while granting the journal non-exclusive publishing and archiving rights and may self-archive without embargo. Third-party material requires proper permission, and the journal ensures long-term free access through its website and archiving partners.
How to Cite
