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

Table 3

Critical review of federated learning (FL) based approaches in ID.

Ref	Authors	Year	Cited by	FL approach	Accuracy (%)
[80]	Supriya and Gadekallu	2023	1	FL-based approach particle swarm optimization (PSO)	94.47
[81]	Mu et al.	2023	16	FedProc: Prototypical contrastive FL	Improves accuracy by 1.6% to 7.9
[82]	Yu et al.	2023	1	FL-based Iron forge approach	97
[83]	Nguyen et al.	2020	78	FL-based IoT IDS	99.9
[84]	Liu et al.	2021	70	FL and Blockchain based IDS	>80
[85]	Chen et al.	2020	54	Federated learning-based attention gated recurrent unit (FedAGRU)	98.82
[86]	Rahman et al.	2020	119	FL-based scheme	83.09
[87]	Mothukuri et al.	2021	173	FL-based anomaly detection approach	90.255
[88]	Zhao et al.	2019	94	Multi-task deep neural network in federated learning (MT-DNN-FL)	96.54
[89]	Rey et al.	2022	93	FL-based malware detection framework	98.59
[90]	Belenguer et al.	2022	6	FL-based application	92
[91]	Zhang et al.	2022	9	SecFedNIDS: Robust defense for poisoning attack against federated learning-based network IDS	Improves 48
[92]	Sarhan et al.	2023	10	Collaborative cyber threat intelligence sharing scheme	92