Home > Research > Publications & Outputs > Towards an autonomous resilience strategy the i...
View graph of relations

Towards an autonomous resilience strategy the implementation of a self evolving rate limiter

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Towards an autonomous resilience strategy the implementation of a self evolving rate limiter. / Ali, Azman; Hutchinson, David; Angelov, Plamen et al.
13th UK Workshop on Computational Intelligence (UKCI), 2013 . Guildford, UK: UKCI 2013, 2013. p. 299-304.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Ali, A, Hutchinson, D, Angelov, P & Smith, P 2013, Towards an autonomous resilience strategy the implementation of a self evolving rate limiter. in 13th UK Workshop on Computational Intelligence (UKCI), 2013 . UKCI 2013, Guildford, UK, pp. 299-304. https://doi.org/10.1109/UKCI.2013.6651320

APA

Ali, A., Hutchinson, D., Angelov, P., & Smith, P. (2013). Towards an autonomous resilience strategy the implementation of a self evolving rate limiter. In 13th UK Workshop on Computational Intelligence (UKCI), 2013 (pp. 299-304). UKCI 2013. https://doi.org/10.1109/UKCI.2013.6651320

Vancouver

Ali A, Hutchinson D, Angelov P, Smith P. Towards an autonomous resilience strategy the implementation of a self evolving rate limiter. In 13th UK Workshop on Computational Intelligence (UKCI), 2013 . Guildford, UK: UKCI 2013. 2013. p. 299-304 doi: 10.1109/UKCI.2013.6651320

Author

Ali, Azman ; Hutchinson, David ; Angelov, Plamen et al. / Towards an autonomous resilience strategy the implementation of a self evolving rate limiter. 13th UK Workshop on Computational Intelligence (UKCI), 2013 . Guildford, UK : UKCI 2013, 2013. pp. 299-304

Bibtex

@inproceedings{a634a293748e4be095265e3d06029808,
title = "Towards an autonomous resilience strategy the implementation of a self evolving rate limiter",
abstract = "Distributed Denial of Service (DDoS) attacks on network infrastructure are one of the major challenges facing network service providers. Despite the recent rise of low-volume application-level attacks, volume-based DDoS attacks still dominate, with peak traffic rates of 80Gbps being observed recently. This prompts the need for more efficient ways to deal with them. Meanwhile, service providers are struggling to acquire the right technology, resources and expertise to offer more resilient and reliable services. One of the solutions to help address this issue is to adopt an autonomous resilience strategy that systematically coordinates resilience related activities such as detecting and mitigating attacks. In this paper, we study an implementation of an autonomous traffic rate limiter - a function that can be used to mitigate DDoS attacks - that capitalises on the AnYa algorithm, an autonomous learning systems (ALS) algorithm that provides advanced features that are crucial to support an autonomous resilience strategy. These features include self-structuring and support for online learning. In our study, we experimentally show how remediation and recovery processes can be realized autonomously, in response to changes in the operational policy.",
author = "Azman Ali and David Hutchinson and Plamen Angelov and Paul Smith",
year = "2013",
month = sep,
doi = "10.1109/UKCI.2013.6651320",
language = "English",
isbn = "9781479915682",
pages = "299--304",
booktitle = "13th UK Workshop on Computational Intelligence (UKCI), 2013",
publisher = "UKCI 2013",

}

RIS

TY - GEN

T1 - Towards an autonomous resilience strategy the implementation of a self evolving rate limiter

AU - Ali, Azman

AU - Hutchinson, David

AU - Angelov, Plamen

AU - Smith, Paul

PY - 2013/9

Y1 - 2013/9

N2 - Distributed Denial of Service (DDoS) attacks on network infrastructure are one of the major challenges facing network service providers. Despite the recent rise of low-volume application-level attacks, volume-based DDoS attacks still dominate, with peak traffic rates of 80Gbps being observed recently. This prompts the need for more efficient ways to deal with them. Meanwhile, service providers are struggling to acquire the right technology, resources and expertise to offer more resilient and reliable services. One of the solutions to help address this issue is to adopt an autonomous resilience strategy that systematically coordinates resilience related activities such as detecting and mitigating attacks. In this paper, we study an implementation of an autonomous traffic rate limiter - a function that can be used to mitigate DDoS attacks - that capitalises on the AnYa algorithm, an autonomous learning systems (ALS) algorithm that provides advanced features that are crucial to support an autonomous resilience strategy. These features include self-structuring and support for online learning. In our study, we experimentally show how remediation and recovery processes can be realized autonomously, in response to changes in the operational policy.

AB - Distributed Denial of Service (DDoS) attacks on network infrastructure are one of the major challenges facing network service providers. Despite the recent rise of low-volume application-level attacks, volume-based DDoS attacks still dominate, with peak traffic rates of 80Gbps being observed recently. This prompts the need for more efficient ways to deal with them. Meanwhile, service providers are struggling to acquire the right technology, resources and expertise to offer more resilient and reliable services. One of the solutions to help address this issue is to adopt an autonomous resilience strategy that systematically coordinates resilience related activities such as detecting and mitigating attacks. In this paper, we study an implementation of an autonomous traffic rate limiter - a function that can be used to mitigate DDoS attacks - that capitalises on the AnYa algorithm, an autonomous learning systems (ALS) algorithm that provides advanced features that are crucial to support an autonomous resilience strategy. These features include self-structuring and support for online learning. In our study, we experimentally show how remediation and recovery processes can be realized autonomously, in response to changes in the operational policy.

U2 - 10.1109/UKCI.2013.6651320

DO - 10.1109/UKCI.2013.6651320

M3 - Conference contribution/Paper

SN - 9781479915682

SP - 299

EP - 304

BT - 13th UK Workshop on Computational Intelligence (UKCI), 2013

PB - UKCI 2013

CY - Guildford, UK

ER -