The Role of Transformers in Modern Cyber Threat Intelligence on Anomaly Detection and Attribution

DOI

10.2991/978-94-6239-616-6_101How to use a DOI?

Keywords

Cyber Threat Intelligence (CTI); Transformer Models; Anomaly Detection; Autonomous Cyber Defense

Abstract

Cyberattacks continue to grow more advanced, making it increasingly difficult for traditional cybersecurity systems to detect and prevent harmful activities in real time. Many existing security solutions depend on predefined rules and known attack signatures, which limits their ability to identify unfamiliar threats or zero-day exploits. They also fail to interpret the sequence patterns and contextual meaning within logs, often leading to unnecessary alerts and slow responses to emerging risks. To address these limitations, this project proposes a real-time log anomaly detection and threat handling system that analyzes logs as they are generated and identifies suspicious behavior before an attack can escalate. The system uses a combination of deep-learning models to understand both long-range behavior and sudden unusual changes in log activity, while semantic processing helps to interpret the true intent of each log message. Events are automatically classified as normal activity, existing threats, or newly emerging anomalies, and administrators are supported with an interactive dashboard where they can block malicious IPs, send alerts, and store new threat samples. The approach enables continuous learning during deployment, improving detection accuracy over time without full retraining requirements. The overall system reduces false positives, increases reliability, and provides a proactive defense strategy, making it suitable for modern enterprise and cloud security environments where threats evolve rapidly.

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  - N. Thilagavathi
AU  - M. Nandhitha
AU  - S. Aswini
AU  - S. Gobika
PY  - 2026
DA  - 2026/03/31
TI  - The Role of Transformers in Modern Cyber Threat Intelligence on Anomaly Detection and Attribution
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 1386
EP  - 1400
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_101
DO  - 10.2991/978-94-6239-616-6_101
ID  - Thilagavathi2026
ER  -