Table 1 Comparative analysis for the related work.
From: Explainable artificial intelligence for botnet detection in internet of things
Algorithm | Author | Ref | Year | Dataset | Objective | No of classes | No of features | Accuracy |
|---|---|---|---|---|---|---|---|---|
RF | Doshi | 2017 | Simulated | DDoS detection in IoT | 2 | 11 | 99.80 | |
DT (J48) | Anthi | 2019 | Simulated | Intrusion detection in smart medical IoT | 2 | 121 | 99.00 | |
DT | Goyal | 2019 | Simulated | Detecting botnets based on behavioral analysis in IoT | 2 | 3 | 87.15 | |
DT | Chaudhary | 2019 | Simulated | DDoS detection in IoT | 2 | NA | 98.34 | |
RF | Chaudhary | 2019 | Simulated | DDoS detection in IoT | 2 | NA | 99.17 | |
RF + ET | Alrashdi | 2019 | UNSW-NB15 | NIDS for IoT | 2 | 49 | 99.34 | |
RF | Thamilarasu | 2020 | Simulated | Intrusion detection for medical IoT | 2 | NA | 100.0 | |
RF | Hammoudeh | 2021 | KDDCup99 | NIDS for IoT | 2 | 41 | 89.39 | |
XGB | Kumar | 2019 | Synthetic | Peer-to-Peer Botnet Detection | 2 | 18 | 99.88 | |
EL ADB | Hazman | 2022 | IoT-23, BoT-IoT, Edge-IIoT | NIDS for Smart cities IoT | 2 | 30 | 99.90 | |
XGB | Khan | 2022 | Elnour et al. HVAC dataset | Attack detection for HVAC | 2 | 24 | 99.98 | |
XGB | Ashraf | 2022 | CICIDS2018, N-BaIoT, KDD Cup 99 | NIDS for Blockchain enabled IoT Healthcare | 2 | 10 | 98.96 | |
XGB/DT | Alissa | 2022 | UNSWNB15 | Botnet attack detection in IoT | 2 | 40 | 94.00 | |
XGB LGB | Garg | 2022 | BoT-IoT, IoT-23, CICDDoS-19 | Attacks Identification: IoT attacks and DDoS attacks | 2 | 35 | 94.49 94.79 | |
LGB PSO-LGB GSA-LGB | Bhoi | 2022 | IoT dataset | Identification of Malicious Access in IoT Network | 2 | 13 | 99.99 100.0 100.0 | |
HGB | Saied | 2025 | N-BaIoT | IoT Botnet Attack Detection | 2 | 115 | 99.99 | |
HGB | Saied | 2023 | N-BaIoT | IoT Botnet Attack Detection | 3 | 115 | 99.99 |
