Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Summary of meta-learning related works.

More »

Table 1 Expand

Table 2.

Summary of self-attention related works.

More »

Table 2 Expand

Table 3.

Summary of few-shot IoT intrusion detection works.

More »

Table 3 Expand

Fig 1.

The overall architecture of MACML-IDS.

More »

Fig 1 Expand

Fig 2.

The overall architecture of the MAC module.

More »

Fig 2 Expand

Fig 3.

Training process of the MAC module.

More »

Fig 3 Expand

Table 4.

Data types in CICIoT2023 dataset.

More »

Table 4 Expand

Table 5.

Data types in CICIDS2018 dataset.

More »

Table 5 Expand

Table 6.

Hyperparameter settings for MACML-IDS.

More »

Table 6 Expand

Fig 4.

Accuracy trends during training.

More »

Fig 4 Expand

Fig 5.

Detection rate trends during training.

More »

Fig 5 Expand

Fig 6.

MACML-IDS performance evaluation on CICIoT2023 dataset with different training sample sizes.

More »

Fig 6 Expand

Fig 7.

MACML-IDS performance evaluation on CICIDS2018 dataset with different training sample sizes.

More »

Fig 7 Expand

Table 7.

F1-score for different attack types with different training sample sizes.

More »

Table 7 Expand

Fig 8.

Data distribution of the results of testing all attack types (CICIoT2023).

More »

Fig 8 Expand

Fig 9.

Data distribution of the results of testing all attack types (CICIDS2018).

More »

Fig 9 Expand

Table 8.

Cross-domain detection results on CICIoT2023.

More »

Table 8 Expand

Table 9.

Cross-domain detection results on CICIDS2018.

More »

Table 9 Expand

Fig 10.

Comparison of same-domain and cross-domain experimental results on CICIoT2023.

More »

Fig 10 Expand

Fig 11.

Comparison of same-domain and cross-domain experimental results on CICIDS2018.

More »

Fig 11 Expand

Fig 12.

Data distribution of the cross-domain experimental results on CICIoT2023.

More »

Fig 12 Expand

Fig 13.

Data distribution of the cross-domain experimental results on CICIDS2018.

More »

Fig 13 Expand

Table 10.

Comparison between MACML-IDS and related work.

More »

Table 10 Expand

Fig 14.

Visualization of the CICIoT2023 dataset.

More »

Fig 14 Expand

Fig 15.

Visualization of the CICIDS2018 dataset.

More »

Fig 15 Expand

Fig 16.

Heatmaps of average confusion matrices in 1, 5 and 10-shot scenarios.

More »

Fig 16 Expand

Fig 17.

Multiclass detection results in 1, 5 and 10-shot scenarios.

More »

Fig 17 Expand