# IoT/IoMT Attack Detection on CICIoT 2023 (test) Source: [IoT/IoMT Attack Detection on CICIoT 2023 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:52:05.619Z Evaluation of models for general IoT and IoMT attack detection performance using the test split of the CICIoT 2023 dataset, reporting mean precision, recall, F1 score, and overall accuracy. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | IoT/IoMT Attack Detection | | Dataset (including any stated split) | CICIoT 2023 (test) | | Metric | Mean F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 31 of 31 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Mean F1 Score](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. - [Mean Precision](): Higher is better; unit: PERCENT. - [Mean Recall](): Higher is better; unit: PERCENT. - [AUC](): Higher is better; unit: PERCENT. - [AP](): Higher is better; unit: PERCENT. - [TNR](): Higher is better; unit: PERCENT. - [NPV](): Higher is better; unit: PERCENT. - [FPR](): Lower is better; unit: PERCENT. - [FNR](): Lower is better; unit: PERCENT. - [TP](): Higher is better; unit: SCALAR. - [TN](): Higher is better; unit: SCALAR. - [FP](): Lower is better; unit: SCALAR. - [FN](): Lower is better; unit: SCALAR. ## Recorded results | Method | Mean F1 Score | Result date | Report paper | | --- | --- | --- | --- | | SHapley Additive exPlanations (SHAP)-based attribution fingerprinting | 99.78 | Not recorded | 6912c2ee2828b7cc6937d9e0 | | SHapley Additive exPlanations (SHAP)-based attribution fingerprinting | 99.51 | Not recorded | 6912c2ee2828b7cc6937d9e0 | | SHapley Additive exPlanations (SHAP)-based attribution fingerprinting | 99.29 | Not recorded | 6912c2ee2828b7cc6937d9e0 | | LDM | 99 | Not recorded | 6976f52fa2b28e761d87c322 | | LDM | 99 | Not recorded | 6976f52fa2b28e761d87c322 | | DM | 97 | Not recorded | 6976f52fa2b28e761d87c322 | | VAE | 96 | Not recorded | 6976f52fa2b28e761d87c322 | | Adversarially Trained Model | 94.58 | Not recorded | 6912c2ee2828b7cc6937d9e0 | | GAN | 94 | Not recorded | 6976f52fa2b28e761d87c322 | | Adversarially Trained Model | 93.3 | Not recorded | 6912c2ee2828b7cc6937d9e0 | | DM | 92 | Not recorded | 6976f52fa2b28e761d87c322 | | SMOTE | 89 | Not recorded | 6976f52fa2b28e761d87c322 | | VAE | 86 | Not recorded | 6976f52fa2b28e761d87c322 | | GAN | 83 | Not recorded | 6976f52fa2b28e761d87c322 | | Adversarially Trained Model | 78.62 | Not recorded | 6912c2ee2828b7cc6937d9e0 | | Traffic-MoE | 78.24 | Not recorded | 695b455a53fdd5c361742e4b | | NetGPT | 69.62 | Not recorded | 695b455a53fdd5c361742e4b | | SMOTE | 66 | Not recorded | 6976f52fa2b28e761d87c322 | | TrafficFormer | 65.94 | Not recorded | 695b455a53fdd5c361742e4b | | DM | 53 | Not recorded | 6976f52fa2b28e761d87c322 | | ET-BERT | 52.17 | Not recorded | 695b455a53fdd5c361742e4b | | AppScanner | 46.19 | Not recorded | 695b455a53fdd5c361742e4b | | Baseline | 46 | Not recorded | 6976f52fa2b28e761d87c322 | | LDM | 44 | Not recorded | 6976f52fa2b28e761d87c322 | | FS-Net | 40.94 | Not recorded | 695b455a53fdd5c361742e4b | | SMOTE | 35 | Not recorded | 6976f52fa2b28e761d87c322 | | VAE | 34 | Not recorded | 6976f52fa2b28e761d87c322 | | GAN | 33 | Not recorded | 6976f52fa2b28e761d87c322 | | FlowPrint | 19.89 | Not recorded | 695b455a53fdd5c361742e4b | | Baseline | 17 | Not recorded | 6976f52fa2b28e761d87c322 | | Baseline | 0 | Not recorded | 6976f52fa2b28e761d87c322 | ### SHapley Additive exPlanations (SHAP)-based attribution fingerprinting Mean F1 Score: 99.78. Result ID: 699af44f5698665ec4859d12. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacks":"PGD"}. This record does not assert independent reproduction. ### SHapley Additive exPlanations (SHAP)-based attribution fingerprinting Mean F1 Score: 99.51. Result ID: 699af44f5698665ec4859d11. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacks":"FGSM"}. This record does not assert independent reproduction. ### SHapley Additive exPlanations (SHAP)-based attribution fingerprinting Mean F1 Score: 99.29. Result ID: 699af44f5698665ec4859d13. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacks":"DeepFool"}. This record does not assert independent reproduction. ### LDM Mean F1 Score: 99. Result ID: 69991e6a5698665ec48547fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### LDM Mean F1 Score: 99. Result ID: 69991e6a5698665ec4854800. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### DM Mean F1 Score: 97. Result ID: 69991e6a5698665ec48547f9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### VAE Mean F1 Score: 96. Result ID: 69991e6a5698665ec48547f7. [Reporting paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### Adversarially Trained Model Mean F1 Score: 94.58. Result ID: 699af44f5698665ec4859d15. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacks":"PGD"}. This record does not assert independent reproduction. ### GAN Mean F1 Score: 94. Result ID: 69991e6a5698665ec48547f8. [Reporting paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### Adversarially Trained Model Mean F1 Score: 93.3. Result ID: 699af44f5698665ec4859d14. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacks":"FGSM"}. This record does not assert independent reproduction. ### DM Mean F1 Score: 92. Result ID: 69991e6a5698665ec48547ff. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### SMOTE Mean F1 Score: 89. Result ID: 69991e6a5698665ec48547f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### VAE Mean F1 Score: 86. Result ID: 69991e6a5698665ec48547fd. [Reporting paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### GAN Mean F1 Score: 83. Result ID: 69991e6a5698665ec48547fe. [Reporting paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### Adversarially Trained Model Mean F1 Score: 78.62. Result ID: 699af44f5698665ec4859d16. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Attacks":"DeepFool"}. This record does not assert independent reproduction. ### Traffic-MoE Mean F1 Score: 78.24. Result ID: 6996f7bb5698665ec4447b00. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"paradigm":"Pre-training and Fine-tuning"}. This record does not assert independent reproduction. ### NetGPT Mean F1 Score: 69.62. Result ID: 6996f7bb5698665ec4447afe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"paradigm":"Pre-training and Fine-tuning"}. This record does not assert independent reproduction. ### SMOTE Mean F1 Score: 66. Result ID: 69991e6a5698665ec48547fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### TrafficFormer Mean F1 Score: 65.94. Result ID: 6996f7bb5698665ec4447aff. [Reporting paper]() Recorded evaluation configuration: {"paradigm":"Pre-training and Fine-tuning"}. This record does not assert independent reproduction. ### DM Mean F1 Score: 53. Result ID: 69991e6a5698665ec4854805. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### ET-BERT Mean F1 Score: 52.17. Result ID: 6996f7bb5698665ec4447afd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"paradigm":"Pre-training and Fine-tuning"}. This record does not assert independent reproduction. ### AppScanner Mean F1 Score: 46.19. Result ID: 6996f7bb5698665ec4447afa. [Reporting paper]() Recorded evaluation configuration: {"paradigm":"Machine Learning (ML)"}. This record does not assert independent reproduction. ### Baseline Mean F1 Score: 46. Result ID: 69991e6a5698665ec48547f5. [Reporting paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"None (Imbalanced)"}. This record does not assert independent reproduction. ### LDM Mean F1 Score: 44. Result ID: 69991e6a5698665ec4854806. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### FS-Net Mean F1 Score: 40.94. Result ID: 6996f7bb5698665ec4447afc. [Reporting paper]() Recorded evaluation configuration: {"paradigm":"Deep Learning (DL)"}. This record does not assert independent reproduction. ### SMOTE Mean F1 Score: 35. Result ID: 69991e6a5698665ec4854802. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### VAE Mean F1 Score: 34. Result ID: 69991e6a5698665ec4854803. [Reporting paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### GAN Mean F1 Score: 33. Result ID: 69991e6a5698665ec4854804. [Reporting paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"Augmented to class balance"}. This record does not assert independent reproduction. ### FlowPrint Mean F1 Score: 19.89. Result ID: 6996f7bb5698665ec4447afb. [Reporting paper]() Recorded evaluation configuration: {"paradigm":"Machine Learning (ML)"}. This record does not assert independent reproduction. ### Baseline Mean F1 Score: 17. Result ID: 69991e6a5698665ec48547fb. [Reporting paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"None (Imbalanced)"}. This record does not assert independent reproduction. ### Baseline Mean F1 Score: 0. Result ID: 69991e6a5698665ec4854801. [Reporting paper]() Recorded evaluation configuration: {"Detection Model":"Ensemble (subspace method, 100 cycles)","Data Balancing":"None (Imbalanced)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.