Intrusion Detection System using Metaheuristic Algorithm

Saraswathi, K.; Gayathridevi, S.; Renukadevi, N. T.; Kumar, Manoj

doi:10.1109/gcat52182.2021.9587486

Cited by 4 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The findings demonstrate notable improvements in detection rate, accuracy, and false alarm reduction compared to existing state-of-the-art classifiers. [16] propose a high-performance classification algorithm, SEKS, and SEIDS, for improving attack detection in an IDS. Their approach combines clustering, classification, and metaheuristic algorithms to enhance accuracy and detect unfamiliar attacks.…”

Section: Related Workmentioning

confidence: 99%

“…Key findings [9] Feature selection Usage of Information Gain (IG), Gain Ratio (GR), Symmetrical Un-certainty (SU), Relief-F (R-F), One-R (OR) and Chi-Square (CS) for feature selection from network traffic to create IDS [10] Recursive feature elimination mechanism and a decision tree-based classifier Improved accuracy in comparison to literature [11] MultiTree algorithm A selection of base classifiers such as decision tree, random forest, kNN, and DNN is employed to enhance the overall detection effectiveness [12] Hybrid approach PSO, GA and DE used in tandem with kNN and DT for classification [13] Metaheuristic algorithm Only GA is used for feature selection [14] Metaheuristic MQBHOA MQBHOA algorithm used in tandem with KNN for classification [15] Machine learning RF with KNN, DR, SVM, LR, NB classifiers used for classification [16] Hybrid approach Clustering, classification and metaheuristic algorithms used…”

Section: Techniquementioning

confidence: 99%

See 1 more Smart Citation

Leveraging Metaheuristics for Feature Selection With Machine Learning Classification for Malicious Packet Detection in Computer Networks

Shanbhag,

Vincent,

Gowda

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Robust Intrusion Detection Systems (IDS) are increasingly necessary in the age of big data due to the growing volume, velocity, and variety of data generated by modern networks. Metaheuristic algorithms offer a promising approach to enhance IDS performance in terms of optimal feature selection. Combining these algorithms along with Machine learning (ML) for the creation of an IDS makes it possible to improve detection accuracy, reduce false positives and negatives, and enhance the efficiency of network monitoring. Our study proposes using metaheuristic algorithms along with machine learning classifiers for feature selection to optimize the number of features from the data set of computer network traffic. We have tested several combinations of algorithms viz., Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and Grey Wolf Optimizer (GWO) along with ML algorithms viz., Decision Tree (DT), Random Forest (RF), Gaussian Naïve Bayes (GNB) and Logistic Regression (LR). The combinations of algorithms have been tested over the NSS-KDD and kddcupdata_10% data sets. We have drawn several insights on feature selection scores with respect to test scores, FI scores, recall and precision for various algorithm combinations. The feature selection time has also been highlighted to showcase the fastest-performing algorithm combinations. Ultimately, we have presented three combinations of algorithms depending on organizational IDS requirements and provided separate solutions for each.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Techniquementioning

confidence: 99%

Leveraging Metaheuristics for Feature Selection With Machine Learning Classification for Malicious Packet Detection in Computer Networks

Shanbhag,

Vincent,

Gowda

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Calculating the fuzzy coefficient of each cluster and figuring out how closely the elements are related to each other in the same cluster by Equation (8). Otherwise, the operation will be repeated from Equation (4) for points that do not belong to any cluster.…”

Section: Editing Clustermentioning

confidence: 99%

“…As a result, such a system is incapable of adapting to the speeds at which cyber threats operate. As a result, swarm intelligence (SI) adds flexibility and learning capability to cyber protection systems to combat cybercrime [7][8][9].…”

mentioning

confidence: 99%

An enhanced mechanism for detection of Domain Name System‐based distributed reflection denial of service attacks depending on modified metaheuristic algorithms and adaptive thresholding techniques

et al. 2022

View full text Add to dashboard Cite

The rapid growth of the number of devices connected to the Internet and the increasing demand for electronic services have led to a huge growth in the number of cyberattacks targeting cyberspace and the development of their methodology. Therefore, there must be mechanisms, laws, and rules regulating the work of these applications and protecting them from electronic attacks. The Domain Name System (DNS) has several vulnerabilities that can be exploited by cyber attackers to launch their attacks, and the most important one of these vulnerabilities is that the response size is always greater than the size of the request. According to reports published by numerous security companies, distributed reflection denial of service (DRDoS) attacks against DNS are regarded as one of the most hazardous and rapidly spreading threats in recent years. An enhanced mechanism that is able to detect DNS-based DRDoS attacks that exploit the DNS responses to launch their attacks is proposed. The proposed mechanism was designed based on modified metaheuristic optimization algorithms and an adaptive threshold. This mechanism consists of two models and four stages. The first model is called 'Proactive Feature Selection,' and the second model is called 'Evolving Dynamic Fuzzy Clustering.' The four stages of the proposed mechanism are: the preprocessing stage, feature selection stage, detection stage, and enhancement stage. The new mechanism has been implemented on the CICDDoS2019 standard dataset and achieves a detection accuracy of 95.44% with a false-positive rate of 0.22%. The results show that the new mechanism is better than others depending on the detection accuracy and false positives. | INTRODUCTIONWith the increase in the number of Internet-connected assets, the effect of distributed denial of service (DDoS) attacks increases proportionately. Due to the nature of this extremely disruptive attack, the level to which its service quality is disrupted and degraded is uncertain [1]. As a result of the widespread use of these services, cyberattacks on the infrastructure of the systems that utilise them become an attractive target [2,3].DDoS Attack is the most frequently used type of cyberattack to disrupt these services [4]. Recent years have seen an explosion in the growth of information security infrastructure and services, such as payment gateways, search engines, banks, and social media websites. This has resulted in an exponential increase in network traffic, increasing Internet misuse. In addition to, security and privacy concerns instil fear in end users, preventing them from using online services [5]. Although proposals and implementations for information security management haveThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

A Deep and Systematic Review of the Intrusion Detection Systems Based on Machine Learning and Deep Learning Techniques

N K,

Ravindran,

et al. 2024

2024 10th International Conference on Advanced Computing and Communication Systems (ICACCS)

View full text Add to dashboard Cite

Intrusion Detection System using Metaheuristic Algorithm

Cited by 4 publications

References 11 publications

Leveraging Metaheuristics for Feature Selection With Machine Learning Classification for Malicious Packet Detection in Computer Networks

Leveraging Metaheuristics for Feature Selection With Machine Learning Classification for Malicious Packet Detection in Computer Networks

An enhanced mechanism for detection of Domain Name System‐based distributed reflection denial of service attacks depending on modified metaheuristic algorithms and adaptive thresholding techniques

A Deep and Systematic Review of the Intrusion Detection Systems Based on Machine Learning and Deep Learning Techniques

Contact Info

Product

Resources

About