A Lightweight Agentic AI Framework with DeepSeek-R1 for Adaptive Phishing URL Detection
Proceedings of the AAAI Symposium Series · 23.06.2026 · 9 (1) · 35-42
DOI: 10.1609/aaaiss.v9i1.42903 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 23.06.2026. Verfasst von Akshat Gaurav und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Phishing URLs remain a major cybersecurity threat because their development is constantly changing and becoming more deceptive. This study presented an agentic adaptive AI framework that utilizes a large language model as a reasoning agent operating multiple external tools instead of performing a classification, to detect phishing URLs. An lightweight tabular classifier with just 9,662 trainable parameters delivers predictions very efficiently, and explains the relevance of features in terms of attack similarity based on SHAP-based feature attribution and episodic memory retrieval. The agent combines these outputs from the tools to generate structured explanations and security recommendations. Experiments demonstrate strong performance, with accuracy up to 95.6% and AUC values above 0.99.
Zitieren
APA
Gaurav, A., Arya, V., Nayak, A., Chui, K. T., & Gupta, B. B. (2026). A Lightweight Agentic AI Framework with DeepSeek-R1 for Adaptive Phishing URL Detection. Proceedings of the AAAI Symposium Series, 9(1), 35-42. https://doi.org/10.1609/aaaiss.v9i1.42903
Vancouver
Gaurav A, Arya V, Nayak A, Chui KT, Gupta BB. A Lightweight Agentic AI Framework with DeepSeek-R1 for Adaptive Phishing URL Detection. Proceedings of the AAAI Symposium Series. 2026;9(1):35-42. doi:10.1609/aaaiss.v9i1.42903
BibTeX
@article{Gaurav2026,
author = {Gaurav, Akshat and Arya, Varsha and Nayak, Amiya and Chui, Kwok Tai and Gupta, Brij B.},
title = {A Lightweight Agentic AI Framework with DeepSeek-R1 for Adaptive Phishing URL Detection},
journal = {Proceedings of the AAAI Symposium Series},
year = {2026},
volume = {9},
number = {1},
pages = {35--42},
doi = {10.1609/aaaiss.v9i1.42903}
}
EUVIMED