Application of Self Adaptive Differential Evolution for Design of Modern Intrusion Detection System
Keywords:
Differential Evolution, Security, Intrusion, Malicious, MutationAbstract
Intrusion detection plays a pivotal role in safeguarding modern computer networks and systems from evolving cyber threats. To enhance the efficacy of intrusion detection systems (IDS) in detecting diverse and dynamic attack patterns, researchers have increasingly turned to optimization algorithms. Among these, the Differential Evolution (DE) algorithm has emerged as a promising candidate due to its ability to iteratively refine parameter configurations for complex systems. This paper explores the application of the Self Adaptive DE algorithm in intrusion detection. It discusses the conceptual framework of integrating DE with intrusion detection, highlighting the steps involved in parameter optimization and its implications for improving IDS performance. The paper further delves into key challenges, such as addressing adversarial attacks, real-time adaptation, and hybridization with other techniques, scalability, and the interpretability of results. By analyzing the potential future directions and research avenues in this domain, this paper provides a comprehensive overview of the role of Self Adaptive DE in enhancing the capabilities of intrusion detection systems and bolstering cyber defense mechanisms.
References
Kirta, Toomas, and Jüri Kivimaab. "Optimizing it security costs by evolutionary algorithms.",Conference on Cyber Conflict Proceedings, 2010.
Dass, Shuvalaxmi, and Akbar Siami Namin. "Evolutionary algorithms for vulnerability coverage., IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC), IEEE, 2020.
.Kivimaa, Jüri, and Toomas Kirt. "Evolutionary algorithms for optimal selection of security measures " ,European Conference on Cyber Warfare and Security. Academic Conferences International Limited. Vol.172, 2011.
Subashini, P., et al. "Review on intelligent algorithms for cyber security." ,Handbook of Research on Machine and Deep Learning Applications for Cyber Security. IGI Global, pp.1-22, 2020.
Abraham, Ajith, Crina Grosan, and Yuehui Chen. "Cyber security and the evolution in intrusion detection systems." Journal of Engineering and Technology, ISSN:0973-2632, 2005.
Lysenko, Sergii, et al. "A cyberattacks detection technique based on evolutionary algorithms.", IEEE 11th International Conference on Dependable Systems, Services and Technologies (DESSERT), IEEE, 2020.
Dash,Tirtharaj. "A study on intrusion detection using neural networks trained with evolutionary algorithms." Soft Computing 21.10 ISSIN: 2687-2700, 2017.
Hussein, Soodeh, and Behnam Mohammad Hasani Zade. "New hybrid method for attack detection using combination of evolutionary algorithms, SVM, and ANN " Computer Network,s 173: 107168, 2020.
Ong,Yew-Soon. "Towards evolutionary multitasking: a new paradigm in evolutionary computation." Computational Intelligence, Cyber Security and Computational Models: Proceedings of ICC3,.Springer Singapore, 2016.
Shao, Yinan, et al. "Multi-objective neural evolutionary algorithm for combinatorial optimization problems." IEEE transactions on neural networks and learning systems, 2021.
Soni, Sumit, and Bharat Bhushan,"Use of Machine Learning algorithms for designing efficient cyber security solutions." 2019 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT). Vol.1. IEEE, 2019.
Tosh, Deepak, et al. "Establishing evolutionary game models for cyber security information exchange (cybex)." Journal of Computer and System Sciences ,pp.27-52, 2018.
Yavanoglu, Ozlem, and Murat Aydos. "A review on cyber security datasets for machine learning algorithms." ,IEEE international conference on big data (big data). IEEE, 2017.
Aburomman, Abdulla Amin, and Mamun Bin Ibne Reaz. "A novel weighted support vector machines multiclass classifier based on differential evolution for intrusion detection systems." Information Sciences, pp.225-246, 2017.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
