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.

Overview of intrusion detection techniques in CAN.

More »

Table 1 Expand

Fig 1.

Workflow Diagram of the Proposed IDS.

More »

Fig 1 Expand

Table 2.

Description of Car Hacking Dataset.

More »

Table 2 Expand

Fig 2.

Proposed DL and Residual Connection based IDS for AV Attack Detection.

More »

Fig 2 Expand

Table 3.

Layer-wise specifications of the proposed IDS architecture.

More »

Table 3 Expand

Fig 3.

Confusion matrix of the proposed IDS illustrating classification performance across different attack classes.

More »

Fig 3 Expand

Fig 4.

Precision, Recall, F1-Score, and Accuracy Metrics for different attack classes obtained by the proposed IDS.

More »

Fig 4 Expand

Fig 5.

Learning curves showing training and validation accuracy (left) and loss (right) of the proposed IDS.

More »

Fig 5 Expand

Fig 6.

ROC curves of the proposed IDS for various attack classes evaluated at different decision thresholds.

More »

Fig 6 Expand

Table 4.

Training and Testing Accuracy and Loss of the Proposed IDS Across Various Attack Classes.

More »

Table 4 Expand

Table 5.

Performance Metrics of the Proposed IDS on the Validation Dataset Across Various Attack Classes.

More »

Table 5 Expand

Table 6.

Per-seed/per-split class counts and attack rates on the HCRL Car Hacking dataset.

More »

Table 6 Expand

Table 7.

Summary of model performance averaged across three random seeds (11, 42, 99) for each attack type in the HCRL Car-Hacking dataset. Values represent mean ± standard deviation over independently trained models, showing consistent near-perfect detection performance and negligible inter-seed variance.

More »

Table 7 Expand

Fig 7.

Confusion matrices for test splits across multiple seeds and attack types.

More »

Fig 7 Expand

Table 8.

Robustness of the proposed IDS under test-time input perturbations (seed = 11). Gaussian noise was added to timestamps, CAN IDs were shifted by ±1, and DATA bytes were jittered by ±1 within [0,255].

More »

Table 8 Expand

Table 9.

Bootstrap 95% confidence intervals (B = 1000) for F1 and ROC–AUC on the held-out test set (seed = 11).

More »

Table 9 Expand

Table 10.

Results of Ablation analysis of the proposed architecture for cyber attack detection in CAV.

More »

Table 10 Expand

Table 11.

Optimized hyperparameters and their corresponding values used in the proposed IDS.

More »

Table 11 Expand

Table 12.

F1-Score comparison of the proposed IDS with existing state-of-the-art methods on the Car Hacking dataset across four major attack types.

More »

Table 12 Expand

Table 13.

Comparison of the proposed IDS with existing techniques in terms of model complexity (number of trainable parameters).

More »

Table 13 Expand

Fig 8.

LIME-based interpretability visualizations for attack instances classified as Class 1 by the proposed IDS.

More »

Fig 8 Expand

Fig 9.

LIME visual observations highlighting influential features for attack-free (Class 0) instances detected by the proposed IDS.

More »

Fig 9 Expand