A novel random neural network based approach for intrusion detection systems

Ayyaz-Ul-Haq Qureshi, Hadi Larijani, Jawad Ahmad, Nhamoinesu Mtetwa

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    3 Downloads (Pure)

    Abstract

    Computer security and privacy of user specific data is a prime concern in day to day communication. The mass use of internet connected systems has given rise to many vulnerabilities which includes attacks on smart devices. Regular occurrence of such events has made the availability of scalable Intrusion Detection System (IDS) a perilous challenge. An intelligent IDS should be able to stop the malicious activity before it destabilizes the core network and to achieve this goal we propose a novel Random Neural Network based Intrusion Detection System (RNN-IDS) in this paper. The performance is evaluated by training different numbers of input and hidden layer neurons with learning rates on benchmark NSL-KDD dataset for binary classification. To validate the feasibility of proposed scheme, results were compared with existing systems and its performance was evaluated by the detection of novel attacks while obtaining an accuracy of 94.50%.
    Original languageEnglish
    Title of host publication2018 10th Computer Science and Electronic Engineering (CEEC)
    PublisherIEEE
    Pages50-55
    Number of pages5
    ISBN (Electronic)9781538672754
    DOIs
    Publication statusPublished - 28 Mar 2019

    Fingerprint

    Intrusion detection
    Neural networks
    Computer privacy
    Security of data
    Neurons
    Availability
    Internet
    Communication

    Keywords

    • intrusion detection
    • machine learning
    • neural networks
    • NSL-KDD
    • Internet of Things security

    Cite this

    Qureshi, A-U-H., Larijani, H., Ahmad, J., & Mtetwa, N. (2019). A novel random neural network based approach for intrusion detection systems. In 2018 10th Computer Science and Electronic Engineering (CEEC) (pp. 50-55). IEEE. https://doi.org/10.1109/CEEC.2018.8674228
    Qureshi, Ayyaz-Ul-Haq ; Larijani, Hadi ; Ahmad, Jawad ; Mtetwa, Nhamoinesu. / A novel random neural network based approach for intrusion detection systems. 2018 10th Computer Science and Electronic Engineering (CEEC). IEEE, 2019. pp. 50-55
    @inproceedings{18e7c999a4a8403f90c88649b9640dcf,
    title = "A novel random neural network based approach for intrusion detection systems",
    abstract = "Computer security and privacy of user specific data is a prime concern in day to day communication. The mass use of internet connected systems has given rise to many vulnerabilities which includes attacks on smart devices. Regular occurrence of such events has made the availability of scalable Intrusion Detection System (IDS) a perilous challenge. An intelligent IDS should be able to stop the malicious activity before it destabilizes the core network and to achieve this goal we propose a novel Random Neural Network based Intrusion Detection System (RNN-IDS) in this paper. The performance is evaluated by training different numbers of input and hidden layer neurons with learning rates on benchmark NSL-KDD dataset for binary classification. To validate the feasibility of proposed scheme, results were compared with existing systems and its performance was evaluated by the detection of novel attacks while obtaining an accuracy of 94.50{\%}.",
    keywords = "intrusion detection, machine learning, neural networks, NSL-KDD, Internet of Things security",
    author = "Ayyaz-Ul-Haq Qureshi and Hadi Larijani and Jawad Ahmad and Nhamoinesu Mtetwa",
    note = "Acceptance in SAN Changed template to proceedings",
    year = "2019",
    month = "3",
    day = "28",
    doi = "10.1109/CEEC.2018.8674228",
    language = "English",
    pages = "50--55",
    booktitle = "2018 10th Computer Science and Electronic Engineering (CEEC)",
    publisher = "IEEE",

    }

    Qureshi, A-U-H, Larijani, H, Ahmad, J & Mtetwa, N 2019, A novel random neural network based approach for intrusion detection systems. in 2018 10th Computer Science and Electronic Engineering (CEEC). IEEE, pp. 50-55. https://doi.org/10.1109/CEEC.2018.8674228

    A novel random neural network based approach for intrusion detection systems. / Qureshi, Ayyaz-Ul-Haq; Larijani, Hadi; Ahmad, Jawad; Mtetwa, Nhamoinesu.

    2018 10th Computer Science and Electronic Engineering (CEEC). IEEE, 2019. p. 50-55.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    TY - GEN

    T1 - A novel random neural network based approach for intrusion detection systems

    AU - Qureshi, Ayyaz-Ul-Haq

    AU - Larijani, Hadi

    AU - Ahmad, Jawad

    AU - Mtetwa, Nhamoinesu

    N1 - Acceptance in SAN Changed template to proceedings

    PY - 2019/3/28

    Y1 - 2019/3/28

    N2 - Computer security and privacy of user specific data is a prime concern in day to day communication. The mass use of internet connected systems has given rise to many vulnerabilities which includes attacks on smart devices. Regular occurrence of such events has made the availability of scalable Intrusion Detection System (IDS) a perilous challenge. An intelligent IDS should be able to stop the malicious activity before it destabilizes the core network and to achieve this goal we propose a novel Random Neural Network based Intrusion Detection System (RNN-IDS) in this paper. The performance is evaluated by training different numbers of input and hidden layer neurons with learning rates on benchmark NSL-KDD dataset for binary classification. To validate the feasibility of proposed scheme, results were compared with existing systems and its performance was evaluated by the detection of novel attacks while obtaining an accuracy of 94.50%.

    AB - Computer security and privacy of user specific data is a prime concern in day to day communication. The mass use of internet connected systems has given rise to many vulnerabilities which includes attacks on smart devices. Regular occurrence of such events has made the availability of scalable Intrusion Detection System (IDS) a perilous challenge. An intelligent IDS should be able to stop the malicious activity before it destabilizes the core network and to achieve this goal we propose a novel Random Neural Network based Intrusion Detection System (RNN-IDS) in this paper. The performance is evaluated by training different numbers of input and hidden layer neurons with learning rates on benchmark NSL-KDD dataset for binary classification. To validate the feasibility of proposed scheme, results were compared with existing systems and its performance was evaluated by the detection of novel attacks while obtaining an accuracy of 94.50%.

    KW - intrusion detection

    KW - machine learning

    KW - neural networks

    KW - NSL-KDD

    KW - Internet of Things security

    U2 - 10.1109/CEEC.2018.8674228

    DO - 10.1109/CEEC.2018.8674228

    M3 - Conference contribution

    SP - 50

    EP - 55

    BT - 2018 10th Computer Science and Electronic Engineering (CEEC)

    PB - IEEE

    ER -

    Qureshi A-U-H, Larijani H, Ahmad J, Mtetwa N. A novel random neural network based approach for intrusion detection systems. In 2018 10th Computer Science and Electronic Engineering (CEEC). IEEE. 2019. p. 50-55 https://doi.org/10.1109/CEEC.2018.8674228