Advances in Adversarial Attacks and Defenses in Intrusion Detection System: A Survey
Advances in Adversarial Attacks and Defenses in Intrusion Detection System: A Survey
复制标题
入侵检测系统对抗性攻击和防御的进展：调查
DOI：
10.1007/978-981-19-7769-5_15
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Hiroshi Koide
中科院分区：
文献类型：
--
作者：
Mariama Mbow;Kouichi Sakurai;Hiroshi Koide
机器学习是计算机科学的主要方法之一，在计算机视觉、模式识别、自然语言处理、网络安全等领域得到了广泛而成功的应用。在网络安全领域，机器学习算法在网络入侵检测系统（NIDS）中的应用已经取得了可喜的结果，主要是通过采用深度学习进行异常检测，并且仍在增长。然而，机器学习算法容易受到对抗性攻击，导致性能显著下降。对抗性攻击是一种安全威胁，旨在通过操纵学习算法的预测来欺骗它，而对抗性机器学习是研究这种攻击的产生和防御的一个研究领域。研究人员对计算机视觉中的对抗机器学习进行了大量的研究，但对入侵检测系统的研究还不多。然而，在这个关键的入侵检测领域的失败可能会危及整个系统的安全性，需要引起高度重视。本文综述了基于对抗性机器学习的入侵检测的进展，并探讨了针对入侵检测的各种防御技术。最后讨论了它们的局限性，对这一新兴领域未来的研究方向提出了建议。
Machine learning is one of the predominant methods used in computer science and has been widely and successfully applied in many areas such as computer vision, pattern recognition, natural language processing, cyber security etc. In cyber security, the application of machine learning algorithms for network intrusion detection system (NIDS) has seen promising results for anomaly detection mostly with the adoption of deep learning and is still growing. However, machine learning algorithms are vulnerable to adversarial attacks resulting in significant performance degradation. Adversarial attacks are security threats that aim to deceive the learning algorithm by manipulating its predictions, and Adversarial machine learning is a research area that studies both the generation and defense of such attacks. Researchers have extensively worked on the adversarial machine learning in computer vision but not many works in Intrusion detection system. However, failure in this critical Intrusion detection area could compromise the security of an entire system, and need much attention. This paper provides a review of the advancement in adversarial machine learning based intrusion detection and explores the various defense techniques applied against. Finally discuss their limitations for future research direction in this emerging area.