Skip to main content
QUICK REVIEW

[论文解读] The Threat of Adversarial Attacks on Machine Learning in Network Security -- A Survey

Olakunle Ibitoye, Rana Abou-Khamis|arXiv (Cornell University)|Nov 6, 2019
Network Security and Intrusion Detection被引用 45
一句话总结

本综述将对网络安全中的对抗性攻击进行分类,提出用于对抗风险的风险网格图,并分析针对基于 ML 的网络安全攻击的防御。它强调问题空间与特征空间的区别,以及与网络安全应用对齐的分类法。

ABSTRACT

Machine learning models have made many decision support systems to be faster, more accurate, and more efficient. However, applications of machine learning in network security face a more disproportionate threat of active adversarial attacks compared to other domains. This is because machine learning applications in network security such as malware detection, intrusion detection, and spam filtering are by themselves adversarial in nature. In what could be considered an arm's race between attackers and defenders, adversaries constantly probe machine learning systems with inputs that are explicitly designed to bypass the system and induce a wrong prediction. In this survey, we first provide a taxonomy of machine learning techniques, tasks, and depth. We then introduce a classification of machine learning in network security applications. Next, we examine various adversarial attacks against machine learning in network security and introduce two classification approaches for adversarial attacks in network security. First, we classify adversarial attacks in network security based on a taxonomy of network security applications. Secondly, we categorize adversarial attacks in network security into a problem space vs feature space dimensional classification model. We then analyze the various defenses against adversarial attacks on machine learning-based network security applications. We conclude by introducing an adversarial risk grid map and evaluating several existing adversarial attacks against machine learning in network security using the risk grid map. We also identify where each attack classification resides within the adversarial risk grid map.

研究动机与目标

  • 提出在网络安全背景下的机器学习技术、任务和深度的分类法。
  • 对网络安全中的 ML 应用进行分类,并将对抗性攻击映射到这些应用。
  • 引入针对网络安全中的对抗性攻击的“问题空间 vs. 特征空间”维度分类。
  • 定义并应用对抗性风险框架和网格图来评估攻击情景。
  • 回顾针对基于 ML 的网络安全中的对抗性攻击的防御,并识别存在的空白与未来方向。

提出的方法

  • 提供一个三维 ML 分类(学习任务、技术和深度)作为组织网络安全 ML 应用的基础。
  • 基于网络安全应用开发对抗性攻击的分类法,并引入问题空间 vs. 特征空间的分类。
  • 引入对抗性风险网格图以评估攻击的可能性和严重性,并在该网格中对攻击进行分类。
  • 综合现有对抗性攻击方法与防御,参考先前工作,聚焦于网络安全。
  • 在网络安全背景下比较攻击者知识模型(white/gray/black box)与攻击策略(evasion, poisoning, oracle)。

实验结果

研究问题

  • RQ1如何针对基于 ML 的网络安全应用对对抗性攻击进行具体分类?
  • RQ2问题空间与特征空间区分对网络安全中对抗性攻击设计的影响是什么?
  • RQ3如何通过对抗性风险网格图量化对基于 ML 的网络安全系统的攻击的可能性和严重性?
  • RQ4在网络安全领域的 ML 对抗性攻击中存在哪些防御措施,存在哪些空白?
  • RQ5在所提出的对抗性风险框架中,不同的攻击分类位于何处?

主要发现

  • 引入了一个针对网络安全应用的新对抗性攻击分类法。
  • 提出了针对网络安全中的对抗性攻击的问题空间 vs. 特征空间维度分类。
  • 引入一个对抗性风险网格图,用于评估跨越各安全任务的攻击可能性和影响。
  • 在网络安全背景下对现有的对抗性攻击和防御进行评审与分类。
  • 强调在基于 ML 的网络安全中攻击者与防御者之间的军备竞赛,并概述未来工作方向。

更好的研究,从现在开始

从论文设计到论文写作,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。