智能DoS与DDoS检测：基于GRU-NTM的混合方法
密码学与安全
2025-04-11 v1 机器学习
摘要
检测Denial of Service（DoS）和Distributed Denial of Service（DDoS）攻击是网络安全中的紼要性挑战。本研究引入一种混合深度学习模型，将Gated Recurrent Units（GRUs）和Neural Turing Machine（NTM）结合，用于增强入侵检测。该模型在UNSW-NB15和BoT-IoT数据集上训练，采用GRU层处理序列数据并使用NTM进行长期模式识别。所提出的方法在区分正常流量、DoS流量和DDoS流量方面达到99%的准确率。这些发现为实时威胁检测提供了有前景的进展，促进了网络安全在各个领域的改进。
引用
@article{arxiv.2504.07478,
title = {Intelligent DoS and DDoS Detection: A Hybrid GRU-NTM Approach to Network Security},
author = {Caroline Panggabean and Chandrasekar Venkatachalam and Priyanka Shah and Sincy John and Renuka Devi P and Shanmugavalli Venkatachalam},
journal= {arXiv preprint arXiv:2504.07478},
year = {2025}
}
备注
Accepted at the 2024 5th International Conference on Smart Electronics and Communication (ICOSEC). This is the accepted manuscript version. The final version is published by IEEE at https://doi.org/10.1109/ICOSEC61587.2024.10722438