...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International Journal of Innovative Computing Information and Control >AN ENHANCED ONLINE PHISHING E-MAIL DETECTION FRAMEWORK BASED ON 'EVOLVING CONNECTIONIST SYSTEM'
【24h】

AN ENHANCED ONLINE PHISHING E-MAIL DETECTION FRAMEWORK BASED ON 'EVOLVING CONNECTIONIST SYSTEM'

机译：基于“不断发展的连接者系统”的增强型网络钓鱼电子邮件检测框架

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

One of the main problems in Internet security is unknown "zero-day" phish-ing e-mail attack, a new phishing e-mail that has not been trained on the old data sample or blacklisted. Existing phishing e-mail prevention mechanisms do not perform well against zero-day phishing e-mail attacks. This paper introduces a novel framework, called phishing dynamic evolving neural fuzzy framework (PDENFF), which adapts the "evolving connectionist system" based on a hybrid (supervised/unsupervised) learning approach. PDENFF adaptive online is enhanced by offline learning to detect dynamically the unknown zero-day phishing e-mails. Our analyses have shown that this framework is designed for high-speed "life-long" learning with low memory footprint and minimizes the complexity of the rule base and configuration. This framework achieves high performance, including high level of accuracy, true positive, and true negative results that reached up to 99%, 97%, and 98%, respectively, and an improvement between 3% and 13% comparison of the generated existing solutions to zero-day phishing e-mail exploits.
机译：Internet安全中的主要问题之一是未知的“零日”仿冒电子邮件攻击，这是一种未经过旧数据样本训练或未列入黑名单的新仿冒电子邮件。现有的网络钓鱼电子邮件防护机制在抵御零日网络钓鱼电子邮件攻击方面效果不佳。本文介绍了一种称为网络钓鱼动态演化神经模糊框架（PDENFF）的新颖框架，该框架适用于基于混合（监督/无监督）学习方法的“演化连接主义系统”。通过脱机学习来动态检测未知的零日钓鱼邮件，PDENFF自适应在线功能得到了增强。我们的分析表明，此框架是为内存量少的高速“终身”学习而设计的，并最大程度地减少了规则库和配置的复杂性。该框架可实现高性能，包括高水平的准确性，真实的阳性结果和真实的阴性结果，分别达到高达99％，97％和98％的水平，并且与现有解决方案相比可提高3％至13％零日钓鱼邮件攻击。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号