Towards Evaluation of NIDSs in Adversarial Setting

被引:46
作者
Hashemi, Mohammad J. [1 ]
Cusack, Greg [1 ]
Keller, Eric [1 ]
机构
[1] Univ Colorado, Boulder, CO 80309 USA
来源
BIG-DAMA'19: PROCEEDINGS OF THE 3RD ACM CONEXT WORKSHOP ON BIG DATA, MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE FOR DATA COMMUNICATION NETWORKS | 2019年
基金
美国国家科学基金会;
关键词
Intrusion Detection Systems; Neural Networks; Anomaly Detection; Adversarial Example;
D O I
10.1145/3359992.3366642
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Signature-based Network Intrusion Detection Systems (NIDSs) have traditionally been used to detect malicious traffic, but they are incapable of detecting new threats. As a result, anomaly-based NIDSs, built on neural networks, are beginning to receive attention due to their ability to seek out new attacks. However, it has been shown that neural networks are vulnerable to adversarial example attacks in other domains. But, previously proposed anomaly-based NIDSs have not been evaluated in such adversarial settings. In this paper, we show how to evaluate an anomaly-based NIDS trained on network traffic in the face of adversarial inputs. We show how to craft adversarial inputs in the highly constrained network domain, and we evaluate 3 recently proposed NIDSs in an adversarial setting.
引用
收藏
页码:14 / 21
页数:8
相关论文
共 29 条
  • [1] Deep Learning Approach Combining Sparse Autoencoder With SVM for Network Intrusion Detection
    Al-Qatf, Majjed
    Yu Lasheng
    Al-Habib, Mohammed
    Al-Sabahi, Kamal
    [J]. IEEE ACCESS, 2018, 6 : 52843 - 52856
  • [2] [Anonymous], 2018, COMPUTER VISION PATT
  • [3] [Anonymous], 2015, INT C LEARN REPR ICL
  • [4] [Anonymous], 2018, DEEP LEARN SEC WORKS
  • [5] [Anonymous], 2016, CYB ATT UKR CRIT INF
  • [6] [Anonymous], 2018, P AAAI 2018
  • [7] [Anonymous], TITLE ERROR
  • [8] Biggio B., 2017, Evasion attacks against machine learning at test time
  • [9] Towards Evaluating the Robustness of Neural Networks
    Carlini, Nicholas
    Wagner, David
    [J]. 2017 IEEE SYMPOSIUM ON SECURITY AND PRIVACY (SP), 2017, : 39 - 57
  • [10] Chalapathy R., 2019, CORR