A Critical Review of Artificial Intelligence Based Approaches in Intrusion Detection: A Comprehensive Analysis

Table 1

Critical review of machine learning (ML) based approaches in ID.

Ref	Authors	Year	Cited by	ML approach	Accuracy (%)
[33]	Ahmed et al.	2022	14	Random forest (RF)	95.1
[34]	Singh et al.	2022	15	Support vector Regression	98
[35]	Pranto et al.	2022	9	ML-based ensemble feature selection strategy	99.5
[36]	Raghuvanshi et al.	2022	48	SVM	98
[37]	Albulayhi et al.	2022	28	ML-based IDS	99.98
[38]	Asif et al.	2021	79	ML-based method tangled with the MapReduce-Based intelligent model for ID (MR-IMID)	97.7
[39]	Çavuşoğlu	2019	112	Hybrid and layered IDS	99.7
[40]	Alqahtani et al.	2020	82	RF	94
[41]	Liu and Lang	2019	457	KNN	99
[42]	Ren et al.	2019	80	IDS by using hybrid data optimization (DO-IDS)	92.8
[43]	Bindra and Sood	2019	53	RF	96
[44]	Sai Kiran et al.	2020	43	SVM	98.95
[45]	Saranya et al.	2020	127	RF	99.81
[46]	Logeswari et al.	2023	5	Hybrid feature selection (HFS-light GBM IDS)	98.72
[47]	Muhammad and Saleem	2022	39	Naïve Bayes	98.6