Scholarlink

Class imbalance is a critical challenge in intrusion detection systems, often limiting the effectiveness of classifiers in low-occurrence classes on datasets like CICIDS 2017. We propose a novel framework leveraging Conditional Adversarial Autoencoders (CAAEs) to generate synthetic features for underrepresented attack classes. This augmentation improves dataset balance, leading to better classification performance in intrusion detection systems. By formulating binary classification tasks, we evaluated the impact of CAAE-generated data using Artificial Neural Networks (ANNs). Compared to traditional feature generation techniques like SMOTE, CAAEs achieved superior performance even for minority classes with an average F1-Score of 99.38%.

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

Enhancing Intrusion Detection Systems with Conditional Adversarial Autoencoders for Class Imbalance Mitigation

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Soumyajit Datta,
  • Jaysmito Mukherjee,
  • Kousik DasGupta

摘要

Class imbalance is a critical challenge in intrusion detection systems, often limiting the effectiveness of classifiers in low-occurrence classes on datasets like CICIDS 2017. We propose a novel framework leveraging Conditional Adversarial Autoencoders (CAAEs) to generate synthetic features for underrepresented attack classes. This augmentation improves dataset balance, leading to better classification performance in intrusion detection systems. By formulating binary classification tasks, we evaluated the impact of CAAE-generated data using Artificial Neural Networks (ANNs). Compared to traditional feature generation techniques like SMOTE, CAAEs achieved superior performance even for minority classes with an average F1-Score of 99.38%.