Adversarial Attacks Against IoT Networks using Conditional GAN based Learning

被引:21
作者
Benaddi, Hafsa [1 ]
Jouhari, Mohammed [2 ]
Ibrahimi, Khalil [1 ]
Benslimane, Abderrahim [3 ]
Amhoud, El Mehdi [2 ]
机构
[1] Ibn Tofail Univ, Lab Res Informat LaRI, Fac Sci, Kenitra, Morocco
[2] Mohammed VI Polytech Univ, Sch Comp Sci, Ben Guerir, Morocco
[3] Univ Avignon, CERI LIA, Avignon, France
来源
2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022) | 2022年
关键词
Internet of Things; Network traffic; Deep Learning; Generative Adversarial Network; Intrusion Detection System; Cyberattacks;
D O I
10.1109/GLOBECOM48099.2022.10000726
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
During the last decade, the integration of artificial intelligence (AI) and the use of intrusion detection systems (IDSs) in the Internet of Things(IoT) networks have brought a new dimension to technological progress. Deep learning (DL) and machine learning (ML)-based IDS are vulnerable to adversarial perturbations. However, anomaly detection methods suffer from unbalanced and missing sample data, thus causing IDS training to be complicated. In this paper, we propose using conditional generative adversarial networks (cGANs) to enhance the training process by handling the unbalanced data and coping with the lack of specifics class samples, which may succeed in evading our Convolutional Neural Network-Long Short-Term Memory (CNNLSTM) based-IDS model. We evaluated our proposed IDS model before and after applying the adversarial training using the Bot-IoT dataset. Promising results showed that the accuracy of detecting Theft attacks could be increased by 40%. To the best of our knowledge, we are the first to suggest the combination of cGAN and CNNLSTM based-IDS system to enhance its performance.
引用
收藏
页码:2788 / 2793
页数:6
相关论文
共 15 条
[1]   Smart Home Networks: Security Perspective and ML-based DDoS Detection [J].
Al Mtawa, Yaser ;
Singh, Harsimranjit ;
Haque, Anwar ;
Refaey, Ahmed .
2020 IEEE CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (CCECE), 2020,
[2]  
[Anonymous], 2018, Idsgan: Generative adversarial networks for attack generation against intrusion detection
[3]  
Benaddi H., 2022, IEEE T VEHICULAR TEC
[4]   The robust deep learning-based schemes for intrusion detection in Internet of Things environments [J].
Fu, Xingbing ;
Zhou, Nan ;
Jiao, Libin ;
Li, Haifeng ;
Zhang, Jianwu .
ANNALS OF TELECOMMUNICATIONS, 2021, 76 (5-6) :273-285
[5]   Analyzing Adversarial Attacks Against Deep Learning for Intrusion Detection in IoT Networks [J].
Ibitoye, Olakunle ;
Shafiq, Omair ;
Matrawy, Ashraf .
2019 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2019,
[6]   FGMD: A robust detector against adversarial attacks in the IoT network [J].
Jiang, Hongling ;
Lin, Jinzhi ;
Kang, Haiyan .
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2022, 132 :194-210
[7]  
Jouhari M., 2022, ARXIV220211082
[8]   Towards the development of realistic botnet dataset in the Internet of Things for network forensic analytics: Bot-IoT dataset [J].
Koroniotis, Nickolaos ;
Moustafa, Nour ;
Sitnikova, Elena ;
Turnbull, Benjamin .
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2019, 100 :779-796
[9]   Cloak & Co-locate: Adversarial Railroading of Resource Sharing-based Attacks on the Cloud [J].
Makrani, Hosein Mohammadi ;
Sayadi, Hossein ;
Nazari, Najmeh ;
Khasawneh, Khaled N. ;
Sasan, Avesta ;
Rafatirad, Setareh ;
Homayoun, Houman .
2021 INTERNATIONAL SYMPOSIUM ON SECURE AND PRIVATE EXECUTION ENVIRONMENT DESIGN (SEED 2021), 2021, :1-13
[10]  
Pavate Aruna Animish, 2022, International Journal of Ambient Computing and Intelligence, V13, P1, DOI 10.4018/IJACI.293111