Artificial Intelligence in Fraud Detection and Cybersecurity
i-manager's Journal on Digital Forensics & Cyber Security · 20.12.2026 · 4 (2) · 1
DOI: 10.26634/jdf.4.2.968 ↗Kurz gefasst
Fachartikel in der Zeitschrift i-manager's Journal on Digital Forensics & Cyber Security, online erschienen am 15.12.2026. Verfasst von Ch Sekhar und 1 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben.
Abstract (Originalsprache)
As digital banking accelerates and online commerce grows exponentially, there is an increasing necessity for sophisticated and dependable tools in detecting fraudulent activities. Outdated rules based on traditional approaches cannot suffice for addressing contemporary cybersecurity threats such as sophisticated online scams. This study examines AI's role within finance sectors for addressing those challenges. The text explores methodologies including supervised and unsupervised machine learning, deep learning, NLP through different scholars' approaches, along with metaheuristic optimization methods and graph-based modelling strategies. These innovations offer capabilities such as real-time pattern recognition, predictive analysis, continuous learning, and rapid threat identification. Supervised learning models detect known fraudulent patterns using techniques such as neural networks and decision trees, whereas unsupervised learning models use methods such as clustering and autoencoders to identify previously unknown fraudulent activities. Advanced machine learning techniques enable the efficient processing of large volumes of complex and unstructured data, while natural language processing aids in interpreting textual content and ensuring legal adherence. Advanced techniques like graph-based neural networks (GNNs) and generative artificial intelligence enable financial institutions to model potential fraudulent activities. Despite their effectiveness in minimizing errors and enhancing precision, these techniques encounter difficulties such as unevenly distributed datasets, substantial computational expenses, potential breaches of confidentiality, and susceptibility to adversarial attacks. Future advancements such as federated learning, blockchain technology, and reinforcement learning algorithms, quantum machine learning, and hybrid artificial intelligence architectures are expected to improve the adaptability and security of fraud-detection systems. The document underscores the significance of artificial intelligence in enhancing cybersecurity, operational effectiveness, and consumer confidence within financial institutions.
Zitieren
APA
Sekhar, C., & Eekshita, A. (2026). Artificial Intelligence in Fraud Detection and Cybersecurity. i-manager's Journal on Digital Forensics & Cyber Security, 4(2), 1. https://doi.org/10.26634/jdf.4.2.968
Vancouver
Sekhar C, Eekshita A. Artificial Intelligence in Fraud Detection and Cybersecurity. i-manager's Journal on Digital Forensics & Cyber Security. 2026;4(2):1. doi:10.26634/jdf.4.2.968
BibTeX
@article{Sekhar2026,
author = {Sekhar, Ch and Eekshita, Amujuru},
title = {Artificial Intelligence in Fraud Detection and Cybersecurity},
journal = {i-manager's Journal on Digital Forensics & Cyber Security},
year = {2026},
volume = {4},
number = {2},
pages = {1},
doi = {10.26634/jdf.4.2.968}
}
EUVIMED