EfficientSTNet: A Deep Learning Approach for Multi-Class DDoS Detection
文献类型：期刊论文
| 作者 | Zhang, Lei3; Bai, Yujuan3; Xue, Tao3; Feng GH(冯冠华)2; Zhang, Haibin1 |
| 刊名 | IEEE ACCESS
 |
| 出版日期 | 2025 |
| 卷号 | 13页码:157587-157599 |
| 关键词 | Feature extraction Denial-of-service attack Computer crime Entropy Deep learning Accuracy Floods Telecommunication traffic Computational modeling Autoencoders DDoS DDoS attack detection convolutional neural network deep learning self-attention mechanism |
| ISSN号 | 2169-3536 |
| DOI | 10.1109/ACCESS.2025.3606644 |
| 通讯作者 | Xue, Tao(xuetao01@xidian.edu.cn) ; Feng, Guanhua(fengguanhua@imech.ac.cn) |
| 英文摘要 | DDoS attacks are highly destructive, capable of targeting multiple devices simultaneously and posing significant threats to network systems. Therefore, it is increasingly essential to develop effective and reliable detection methods to ensure network security. Although deep learning techniques improve DDoS detection by autonomously learning feature representations, they still face challenges due to the high dimensionality and noise inherent in network traffic data, which impair computational efficiency and real-time responsiveness. Moreover, their limited adaptability to multi-class classification hinders accurate differentiation of specific attack types. This paper proposes a multi-class DDoS attack detection method based on multi-scale feature modeling-EfficientSTNet. The method employs a selective deep autoencoder for feature selection, then uses a convolutional neural network (CNN) to capture hidden spatial features in network data. Subsequently, a self-attention mechanism extracts temporal features and captures contextual dependencies among different features, improving DDoS attack detection accuracy. Finally, a fully connected layer and normalization compute the probability distribution across different classes, enabling multi-class DDoS detection. Additionally, the method integrates convolution decomposition techniques and residual network structures to accelerate model convergence and improve inference speed. The proposed EfficientSTNet model can identify different types of DDoS attacks, achieving an overall classification accuracy of 99.14% and F1-scores of 97.97% or higher across all categories, demonstrating strong practical application potential. |
| 分类号 | 二类 |
| WOS关键词 | AUTOENCODER |
| 资助项目 | Natural Science Basis Research Plan in Shaanxi Province of China[2025JC-JCQN-089] ; National Natural Science Foundation of China[62302358] ; Doctoral Startup Fund of China (Project Title: Discovery of Advanced Persistent Threat (APT) Attacks Based on Graph Algorithms)[205200100654] ; National Natural Science Foundation of China[62362038] |
| WOS研究方向 | Computer Science ; Engineering ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:001571485600038 |
| 资助机构 | Natural Science Basis Research Plan in Shaanxi Province of China ; National Natural Science Foundation of China ; Doctoral Startup Fund of China (Project Title: Discovery of Advanced Persistent Threat (APT) Attacks Based on Graph Algorithms) ; National Natural Science Foundation of China |
| 其他责任者 | Xue, Tao，冯冠华 |
| 源URL | [http://dspace.imech.ac.cn/handle/311007/103919]  |
| 专题 | 宽域飞行工程科学与应用中心 |
| 作者单位 | 1.Xidian Univ, Sch Cyber Engn, Hangzhou 710126, Peoples R China 2.Chinese Acad Sci, Inst Mech, Beijing 100190, Peoples R China; 3.Xidian Univ, Hangzhou Inst Technol, Hangzhou 710126, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Zhang, Lei,Bai, Yujuan,Xue, Tao,et al. EfficientSTNet: A Deep Learning Approach for Multi-Class DDoS Detection[J]. IEEE ACCESS,2025,13:157587-157599. |
| APA | Zhang, Lei,Bai, Yujuan,Xue, Tao,冯冠华,&Zhang, Haibin.(2025).EfficientSTNet: A Deep Learning Approach for Multi-Class DDoS Detection.IEEE ACCESS,13,157587-157599. |
| MLA | Zhang, Lei,et al."EfficientSTNet: A Deep Learning Approach for Multi-Class DDoS Detection".IEEE ACCESS 13(2025):157587-157599. |
入库方式： OAI收割
来源：力学研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。