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.

Comparison of architectural features of existing CAN intrusion detection methods and the proposed framework.

More »

Table 1 Expand

Fig 1.

Proposed 1D CNN-BiLSTM intrusion detection framework for CAN bus networks.

More »

Fig 1 Expand

Table 2.

Hyperparameter settings of the proposed 1D CNN–Deep BiLSTM intrusion detection model.

More »

Table 2 Expand

Fig 2.

Data preprocessing workflow used for CAN intrusion detection, including feature extraction, normalization, window construction, and attack label assignment.

More »

Fig 2 Expand

Table 3.

Comparative performance analysis of deep learning architectures for CAN intrusion detection.

More »

Table 3 Expand

Table 4.

Wilcoxon signed-rank test results using fold-wise F1-scores obtained from 10-fold cross-validation.

More »

Table 4 Expand

Fig 3.

Performance comparison of intrusion detection models.

More »

Fig 3 Expand

Table 5.

Evaluation results of last-frame and any-attack window labeling methods.

More »

Table 5 Expand

Fig 4.

Performance improvement achieved using any-attack window labeling strategy.

More »

Fig 4 Expand

Table 6.

Performance variation of the proposed model under different decision thresholds.

More »

Table 6 Expand

Table 7.

Performance comparison of different focal loss values.

More »

Table 7 Expand

Fig 5.

Effect of focal loss alpha parameter on IDS performance.

More »

Fig 5 Expand

Fig 6.

Performance comparison between the baseline BiLSTM model from the base paper and the proposed CNN–BiLSTM with focal loss model.

More »

Fig 6 Expand

Table 8.

Performance comparison between the baseline BiLSTM model from the base paper and the proposed CNN–BiLSTM with focal loss model.

More »

Table 8 Expand