ASNM Datasets: A Collection of Network Attacks for Testing of Adversarial Classifiers and Intrusion Detectors

被引:9
|
作者
Homoliak, Ivan [1 ]
Malinka, Kamil [1 ]
Hanacek, Petr [1 ]
机构
[1] Brno Univ Technol, Fac Informat Technol, Ctr Excellence IT4Innovat, Brno 61200, Czech Republic
关键词
Feature extraction; Protocols; Network intrusion detection; Servers; Detectors; Dataset; network intrusion detection; adversarial classification; evasions; ASNM features; buffer overflow; non-payload-based obfuscations; tunneling obfuscations; SQUARE FEATURE-SELECTION; DETECTION SYSTEMS; DATA SET; OPTIMIZATION; CLASSIFICATION; ALGORITHMS; TAXONOMY; ENSEMBLE;
D O I
10.1109/ACCESS.2020.3001768
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we present three datasets that have been built from network traffic traces using ASNM (Advanced Security Network Metrics) features, designed in our previous work. The first dataset was built using a state-of-the-art dataset CDX 2009 that was collected during a cyber defense exercise, while the remaining two datasets were collected by us in 2015 and 2018 using publicly available network services containing buffer overflow and other high severity vulnerabilities. These two datasets contain several adversarial obfuscation techniques that were applied onto malicious as well as legitimate traffic samples during "the execution" of their TCP network connections. Adversarial obfuscation techniques were used for evading machine learning-based network intrusion detection classifiers. We show that the performance of such classifiers can be improved when partially augmenting their training data by samples obtained from obfuscation techniques. In detail, we utilized tunneling obfuscation in HTTP(S) protocol and non-payload-based obfuscations modifying various properties of network traffic by, e.g., TCP segmentation, re-transmissions, corrupting and reordering of packets, etc. To the best of our knowledge, this is the first collection of network traffic data that contains adversarial techniques and is intended for non-payload-based network intrusion detection and adversarial classification. Provided datasets enable testing of the evasion resistance of arbitrary machine learning-based classifiers.
引用
收藏
页码:112427 / 112453
页数:27
相关论文
共 39 条
  • [21] Network Intrusion Detection Adversarial Attacks for LEO Constellation Networks Based on Deep Learning
    Li, Yunhao
    Mo, Weichuan
    Li, Cong
    Wang, Haiyang
    He, Jianwei
    Hao, Shanshan
    Yan, Hongyang
    NETWORK AND SYSTEM SECURITY, NSS 2022, 2022, 13787 : 51 - 65
  • [22] Evaluating and Improving Adversarial Robustness of Machine Learning-Based Network Intrusion Detectors
    Han, Dongqi
    Wang, Zhiliang
    Zhong, Ying
    Chen, Wenqi
    Yang, Jiahai
    Lu, Shuqiang
    Shi, Xingang
    Yin, Xia
    IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2021, 39 (08) : 2632 - 2647
  • [23] NAttack! Adversarial Attacks to bypass a GAN based classifier trained to detect Network intrusion
    Piplai, Aritran
    Chukkapalli, Sai Sree Laya
    Joshi, Anupam
    2020 IEEE 6TH INT CONFERENCE ON BIG DATA SECURITY ON CLOUD (BIGDATASECURITY) / 6TH IEEE INT CONFERENCE ON HIGH PERFORMANCE AND SMART COMPUTING, (HPSC) / 5TH IEEE INT CONFERENCE ON INTELLIGENT DATA AND SECURITY (IDS), 2020, : 49 - 54
  • [24] Evading Deep Reinforcement Learning-based Network Intrusion Detection with Adversarial Attacks
    Merzouk, Mohamed Amine
    Delas, Josephine
    Neal, Christopher
    Cuppens, Frederic
    Boulahia-Cuppens, Nora
    Yaich, Reda
    PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON AVAILABILITY, RELIABILITY AND SECURITY, ARES 2022, 2022,
  • [25] Adversarial Black-Box Attacks Against Network Intrusion Detection Systems: A Survey
    Alatwi, Huda Ali
    Aldweesh, Amjad
    2021 IEEE WORLD AI IOT CONGRESS (AIIOT), 2021, : 34 - 40
  • [26] Adversarial attacks against supervised machine learning based network intrusion detection systems
    Alshahrani, Ebtihaj
    Alghazzawi, Daniyal
    Alotaibi, Reem
    Rabie, Osama
    PLOS ONE, 2022, 17 (10):
  • [27] Defending Convolutional Neural Network-Based Object Detectors Against Adversarial Attacks
    Cheng, Jeffrey
    Hu, Victor
    2020 9TH IEEE INTEGRATED STEM EDUCATION CONFERENCE (ISEC 2020), 2020,
  • [28] Hierarchical Adversarial Attacks Against Graph-Neural-Network-Based IoT Network Intrusion Detection System
    Zhou, Xiaokang
    Liang, Wei
    Li, Weimin
    Yan, Ke
    Shimizu, Shohei
    Wang, Kevin I-Kai
    IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (12) : 9310 - 9319
  • [29] Domain Adversarial Neural Network-Based Intrusion Detection System for In-Vehicle Network Variant Attacks
    Wei, Jingwen
    Chen, Ye
    Lai, Yingxu
    Wang, Yuhang
    Zhang, Zhaoyi
    IEEE COMMUNICATIONS LETTERS, 2022, 26 (11) : 2547 - 2551
  • [30] Constrained optimization based adversarial example generation for transfer attacks in network intrusion detection systems
    Chale, Marc
    Cox, Bruce
    Weir, Jeffery
    Bastian, Nathaniel D.
    OPTIMIZATION LETTERS, 2024, 18 (09) : 2169 - 2188