Scholarlink

This paper explores the application of few-shot learning methods in the detection of network attacks, focusing on evaluating the effectiveness of various machine learning techniques when data availability is limited. The study aims to develop innovative approaches for accurately identifying different types of network attacks with minimal training data, assessing model performance using a range of evaluation metrics. The results highlight the potential of few-shot learning in enhancing cybersecurity applications under data-constrained conditions.

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

Evaluation of Selected Few-Shot Learning Methods in Network Intrusion Detection

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Eryk Winiecki,
  • Marek Pawlicki,
  • Aleksandra Pawlicka,
  • Rafał Kozik,
  • Michał Choraś

摘要

This paper explores the application of few-shot learning methods in the detection of network attacks, focusing on evaluating the effectiveness of various machine learning techniques when data availability is limited. The study aims to develop innovative approaches for accurately identifying different types of network attacks with minimal training data, assessing model performance using a range of evaluation metrics. The results highlight the potential of few-shot learning in enhancing cybersecurity applications under data-constrained conditions.