Scholarlink

<p>In recent years, Distributed Denial of Service (DDoS) attacks have developed one of the greatest communal and disrupting threats to network security. These attacks flood focused systems with traffic, establishment them inaccessible to valid users. The growing intricacy and difficulty of DDoS attacks involve improving strong and adaptable detection methods. Existing DDoS detection systems struggle to discriminate between real and fraudulent network traffic, specifically with high traffic volumes and developing attack approaches. In this study, we proposed a novel Deep Maxout Fusion Convolutional Neural Network (DMFCNN) enabled hybridization model for DDoS attack detection. In this study, we collected the data from the CICIDS2017 dataset for DDoS attack detection. Next, we divide the dataset into training and testing sets. Then, we used a preprocessing methodology, including Min–max normalization. Honey Badger Optimization (HBO) is applied for feature selection. The proposed method is compared to the other traditional algorithms. The overall performance is computed in terms of recall (98.75%), accuracy (95.03%), precision (97.26%), and F1-score (98.03%). These results demonstrate the model’s ability to identify different forms of DDoS attacks with high accuracy, improving network security robustness.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

DMFCNN-HBO: deep maxout fusion convolutional neural network model enabled with honey badger optimization for DDoS attack detection

  • 期刊论文

  • 发表日期：

    2025年1月8日

查看全文
  • Dhananjay Shripad Rakshe,
  • Sweta Jha,
  • Pawan R. Bhaladhare

摘要

In recent years, Distributed Denial of Service (DDoS) attacks have developed one of the greatest communal and disrupting threats to network security. These attacks flood focused systems with traffic, establishment them inaccessible to valid users. The growing intricacy and difficulty of DDoS attacks involve improving strong and adaptable detection methods. Existing DDoS detection systems struggle to discriminate between real and fraudulent network traffic, specifically with high traffic volumes and developing attack approaches. In this study, we proposed a novel Deep Maxout Fusion Convolutional Neural Network (DMFCNN) enabled hybridization model for DDoS attack detection. In this study, we collected the data from the CICIDS2017 dataset for DDoS attack detection. Next, we divide the dataset into training and testing sets. Then, we used a preprocessing methodology, including Min–max normalization. Honey Badger Optimization (HBO) is applied for feature selection. The proposed method is compared to the other traditional algorithms. The overall performance is computed in terms of recall (98.75%), accuracy (95.03%), precision (97.26%), and F1-score (98.03%). These results demonstrate the model’s ability to identify different forms of DDoS attacks with high accuracy, improving network security robustness.