• 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 IMMUNITY-ENHANCING SECURITY MODULE FOR CLOUD SERVERS
【24h】

AN IMMUNITY-ENHANCING SECURITY MODULE FOR CLOUD SERVERS

机译：云服务器的增强免疫力的模块

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

Cyberattacks on a vulnerability in a server application are threats to cloud servers. Advanced endpoint security techniques can detect and mitigate cyberattacks on known and unknown vulnerabilities, but their detection causes the server application to terminate, resulting in a denial of service. Intrusion detection systems with machine learning combine high accuracy and high speed of detection, but they require a wide variety of samples for learning. To solve these drawbacks, this paper proposes an immunity-enhancing module that adaptively acquires immunity to known and unknown cyberattacks without the need for prior learning of attack data. The module consists of innate and adaptive immune functions. The innate immune function detects known and unknown cyberattacks using advanced endpoint security techniques, whereas the adaptive immune function learns and detects the cyberattacks identified by the innate immune function using a gradient boosting classifier, thereby preventing a denial of service due to the innate immune function. This paper describes implementation of the module for a DNS server application. Its performance was evaluated by attacking vulnerabilities of CVE-2015-5477 and CVE-2016-2776. The module showed a detection accuracy of 99.94%, including a true negative rate of 100.00% and a true positive rate of 99.88%, and an overhead of 2.70%.
机译：对服务器应用程序中的漏洞的网络攻击是对云服务器的威胁。先进的端点安全技术可以检测和缓解对已知和未知漏洞的网络攻击，但是它们的检测导致服务器应用程序终止，从而导致拒绝服务。具有机器学习功能的入侵检测系统结合了高精度和高检测速度，但是它们需要各种各样的样本进行学习。为了解决这些缺点，本文提出了一种增强免疫力的模块，该模块可以自适应地获得对已知和未知网络攻击的免疫力，而无需事先学习攻击数据。该模块由先天性和适应性免疫功能组成。先天免疫功能使用先进的端点安全技术检测已知和未知的网络攻击，而自适应免疫功能使用梯度增强分类器学习并检测由先天免疫功能识别的网络攻击，从而防止因先天免疫功能而导致拒绝服务。本文介绍了用于DNS服务器应用程序的模块的实现。通过攻击CVE-2015-5477和CVE-2016-2776漏洞评估了其性能。该模块显示出99.94％的检测精度，包括100.00％的真实阴性率和99.88％的真实阳性率，以及2.70％的开销。

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