arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.08585cs.LGcs.CR
收藏

基于证据理论的高效入侵检测

Efficient Intrusion Detection Using Evidence Theory

Royal Military Academy(皇家军事学院);Université Libre de Bruxelles(布鲁塞尔自由大学)

Islam Debicha, Thibault Debatty, Wim Mees, Jean-Michel Dricot

摘要:

入侵检测系统(IDS)现在是保护计算机和网络安全的重要元素。尽管在该领域进行了大量的研究工作,但处理源的可靠性仍然是一个悬而未决的问题。针对这一问题,本文提出了一种基于信源可靠性及其正常与异常行为区分能力的上下文折扣方法。Dempster-Shafer理论是不确定性推理的一般框架,用于构造证据分类器。NSL-KDD数据集是现有KDDCUP'99数据集的一个重大修订和改进版本,为评估我们新检测方法的性能提供了基础。虽然在KDDTest+数据集上给出了类似的结果,但我们的方法在KDDTest-21数据集上的表现优于其他一些最先进的方法,这更具挑战性。

英文摘要:

Intrusion Detection Systems (IDS) are now an essential element when it comes to securing computers and networks. Despite the huge research efforts done in the field, handling sources' reliability remains an open issue. To address this problem, this paper proposes a novel contextual discounting method based on sources' reliability and their distinguishing ability between normal and abnormal behavior. Dempster-Shafer theory, a general framework for reasoning under uncertainty, is used to construct an evidential classifier. The NSL-KDD dataset, a significantly revised and improved version of the existing KDDCUP'99 dataset, provides the basis for assessing the performance of our new detection approach. While giving comparable results on the KDDTest+ dataset, our approach outperformed some other state-of-the-art methods on the KDDTest-21 dataset which is more challenging.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑