Scholarlink

<p>As Internet of Things (IoT) devices are networked and thus susceptible to many forms of attacks, cyber security risk is the primary concern in the IoT field. To tackle this issue, this study&#xa0;employs machine learning and deep learning techniques to identify botnet attacks. The proposed method uses a random forest classifier or other machine learning techniques to organize the data after extracting detailed characteristics using Bidirectional Long Short-Term Memory (Bi-LSTM). This methodology yields superior outcomes for challenges involving binary and multiclass classification. The IoT-23 and N-BaIoT databases were used. The IoT-23 collection consists of three normal samples and twenty malware samples from different IoT devices, whereas the N-BaIoT dataset includes scenarios like Mirai and Bashlite attacks. In the context of IoT risks, the proposed technique successfully differentiates between benign and malicious traffic data. In terms of multiclass classification, the accuracy rates for N-BaIoT and the IoT-23 dataset are 100% and 99.9%, respectively, while the acquired accuracy rates for binary classification are 99.9% for N-BaIoT and 97% for the IoT-23 dataset.</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

Botnet Detection Through Flow-Based Deep Feature Extraction and Ensemble Classification

  • 期刊论文

  • 发表日期：

    2025年4月27日

查看全文
  • K. Geetha,
  • S. H. Brahmananda

摘要

As Internet of Things (IoT) devices are networked and thus susceptible to many forms of attacks, cyber security risk is the primary concern in the IoT field. To tackle this issue, this study employs machine learning and deep learning techniques to identify botnet attacks. The proposed method uses a random forest classifier or other machine learning techniques to organize the data after extracting detailed characteristics using Bidirectional Long Short-Term Memory (Bi-LSTM). This methodology yields superior outcomes for challenges involving binary and multiclass classification. The IoT-23 and N-BaIoT databases were used. The IoT-23 collection consists of three normal samples and twenty malware samples from different IoT devices, whereas the N-BaIoT dataset includes scenarios like Mirai and Bashlite attacks. In the context of IoT risks, the proposed technique successfully differentiates between benign and malicious traffic data. In terms of multiclass classification, the accuracy rates for N-BaIoT and the IoT-23 dataset are 100% and 99.9%, respectively, while the acquired accuracy rates for binary classification are 99.9% for N-BaIoT and 97% for the IoT-23 dataset.