Table 6. Literature evaluation of streaming data detection in the field of network security.
| Ref. | AD | CD | EC | DP | Explain | Effectiveness | Output | Type |
|---|---|---|---|---|---|---|---|---|
| Bhatia et al. (2022) | Statistical Model | * | AUC, ROC, Acc, Recall | Batch | ✗ | Scalable | Score | Point |
| Tong & Prasanna (2017) | FIM | * | Precision, Recall | Stream | ✗ | Adaptive | Score | Point |
| Hao et al. (2019) | Cluster, LSTM, AE | ✓ | Deland, FPR, ROC-AUC, Recall | Stream | ✗ | Robust | Cluster label | Contextual |
| Hoeltgebaum, Adams & Fernandes (2021) | Statistical Model | ✓ | FD, FP, FN, MSE, MAE | Stream | ✗ | Adaptive | Label | Point |
| Nadler, Aminov & Shabtai (2019) | iForest | * | DR, FPR | Batch | ✓ | Robust | Score | Collective |
| Wambura, Huang & Li (2022) | RNN | * | MAE, ROC-AUC | Stream | ✓ | Scalable, robust | Score | * |
| Xiaolan et al. (2022) | Cluster | ✓ | DR, FAR, Acc | Stream | ✗ | Robust | No | Collective |
| Yin, Li & Yin (2020) | Statistical Model | * | EDR, EFP, END, ENF, EFR | * | ✗ | Robust | Score | Point |
| Zeng et al. (2023b) | Bloom Filter | * | DR, FAR | Stream | ✗ | Robust | Label | Point |
| Wahab (2022) | DNN | ✓ | Precision, Recall, F1, TP, FP, FN, TN, Acc | * | ✗ | Robust | Label | Collective |
| Cai et al. (2022) | K-Means, Cluster | ✓ | Acc | Stream | ✗ | Robust | Label | All |
| Cheng et al. (2020) | TCN | * | Acc, Precision, Recall, F1 | Batch | * | Robust | Label | Collective |
| Jain, Kaur & Saxena (2022) | K-Means, Cluster, SVM | ✓ | Acc, FAR, Precision, Recall, F1, Kappa Statistic | Stream | * | Adaptive, robust | Label | Collective |
| Mirsky et al. (2017) | Cluster | ✓ | ROC, AUC, TPR, FPR | Stream | * | Robust | Score | All |
| Scaranti et al. (2022) | DBSCAN, Entropy | ✓ | Acc, Precision, Recall, F-measure, FAR | Stream | ✗ | Adaptive | Label | All |
| Shao et al. (2023) | Bloom filter | ✓ | Acc | Stream | * | Robust | Label | All |
| Xing, Demertzis & Yang (2020) | e-SNN, REBOM | ✓ | K-Stats, K-Temp-Stats | Stream | * | Robust, scalable | Label | Point |
| Xu et al. (2023) | AE, SVM | ✓ | AUC | Stream | ✗ | Robust | Score | Point |
| Yang et al. (2021) | XGboost | ✓ | AUC | Stream | ✗ | Score | Point | |
| Zeng et al. (2023a) | KDE, AE | ✓ | Recall, Precision, F-score, ROC, TPR, FPR, AUC | Stream | ✗ | Scalable, adaptive, robust | Score | Point |
| Zhou et al. (2020) | Variational LSTM | * | Precision, Recall, F1, FAR, AUC | Batch | ✗ | Scalable | Label | Point |
| Saheed, Abdulganiyu & Tchakoucht (2023) | GWO, ELM, PCA | * | Precision, Recall, DR, Acc | Batch | * | Scalable, robust | Label | Point |
| Yoon et al. (2022) | AE | ✓ | AUC | Batch | ✗ | Scalable, adaptive, robust | Score | Point |
| Yu et al. (2018) | Cluster | * | AUC, Acc | Stream | ✗ | Scalable, adaptive, robust | Score | Point |
Note:
AD, anomaly detection; CD, concept drift; EC, evaluation criteria, DP, data processing mode; FIM, frequency itemset mining; FD, false detection; MAS, mean average score; EDR, event detection rate; EFP, event false positive rate; END, error node detection rate; ENF, error node false positive rate; EFR, error node false recognition rate; *, unknown; ✗, not support; ✓, support.