A Multi-Layered Cybersecurity Framework for Fraud Detection in High-Frequency Stock Markets

DOI

10.2991/978-94-6239-616-6_115How to use a DOI?

Keywords

Cybersecurity; Stock Market Fraud; SECURE Framework; Machine Learning; Intrusion Detection System; Spoofing; Layering

Abstract

High-frequency algorithmic trading environments are prime targets for cyber-enabled attacks such as spoofing, layering, and order injection, which threaten market integrity. Conventional fraud detection methods such as Logistic Regression (LR), Support Vector Machines (SVM), and Random Forests (RF) struggle with real-time anomaly detection, leading to high false alarms and increased latency. To overcome these limitations, this study proposes SECURE (Surveillance, Examination, Control, Understanding, Response, Enhancement), a multi-layer cybersecurity framework integrating machine learning with an Intrusion Detection System (IDS) for adaptive fraud prevention. Three hybrid models (SECURE-CUM-LR, SECURE-CUM-SVM, and SECURE-CUM-RF) were evaluated on synthetic Level 2 stock market data. SECURE-CUM-RF achieved the highest accuracy, lowest false negatives, and microsecond-level detection latency, outperforming both standalone and hybrid models. Results demonstrate that embedding IDS within ML architectures enhances anomaly detection, resilience to temporal drift, and real-time response, offering a scalable solution for securing high-frequency financial infrastructures.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - S. Malathy
AU  - R. Anandhi
AU  - K. Ramya
AU  - S. Sivaranjani
PY  - 2026
DA  - 2026/03/31
TI  - A Multi-Layered Cybersecurity Framework for Fraud Detection in High-Frequency Stock Markets
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 1628
EP  - 1642
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_115
DO  - 10.2991/978-94-6239-616-6_115
ID  - Malathy2026
ER  -