Intrusion Detection on CAR HACKING dataset
99.99PrecisionLSTM-CNN
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| LSTM-CNNAttacks=Fuzzy2025.12 | 99.99 | 99.51 | 99.23 | 99.61 | |
| LSTM-CNNAttacks=DoS2025.12 | 99.98 | 99.48 | 98.28 | 99.12 | |
| LSTM-CNNAttacks=rpm2025.12 | 99.98 | 99.26 | 98.38 | 99.17 | |
| LSTM-CNNAttacks=gear2025.12 | 99.91 | 99.57 | 99.1 | 99.5 | |
| GANAttacks=gear2025.12 | 98.3 | 98 | 90 | — | |
| GANAttacks=rpm2025.12 | 98.1 | 96.2 | 96.5 | — | |
| TCN (autoencoder)Attacks=gear2025.12 | 97.88 | — | 97.84 | 97.86 | |
| GANAttacks=Fuzzy2025.12 | 97.3 | 98 | 99.5 | — | |
| GANAttacks=DoS2025.12 | 96.8 | 97.9 | 99.6 | — | |
| TCN (autoencoder)Attacks=DoS2025.12 | 96.69 | — | 95.62 | 96.08 | |
| TCN (autoencoder)Attacks=rpm2025.12 | 96.41 | — | 96 | 96.17 | |
| TCN (autoencoder)Attacks=Fuzzy2025.12 | 95.25 | — | 95.33 | 95.27 | |
| TransformerAttacks=DoS, Reference=[16]2025.12 | 1 | 1 | 1 | 1 | |
| TransformerAttacks=gear, Reference=[16]2025.12 | 1 | 1 | 1 | 1 | |
| TransformerAttacks=rpm, Reference=[16]2025.12 | 1 | 0.9999 | 1 | 1 | |
| VGG-16Attacks=DoS2025.12 | 1 | 1 | 1 | 1 | |
| VGG-16Attacks=gear2025.12 | 1 | 0.96 | 0.96 | 0.98 | |
| VGG-16Attacks=rpm2025.12 | 1 | 1 | 1 | 1 | |
| TransformerAttacks=DoS, Reference=[4]2025.12 | 1 | — | 1 | 1 | |
| TransformerAttacks=Fuzzy, Reference=[4]2025.12 | 0.9999 | — | 0.9998 | 0.9999 | |
| Graph Convolutional NetworkAttacks=gear2025.12 | 0.9996 | 0.998 | 0.892 | 0.9427 | |
| TransformerAttacks=Normal, Reference=[4]2025.12 | 0.9993 | — | 1 | 0.9996 | |
| TransformerAttacks=rpm, Reference=[4]2025.12 | 0.9984 | — | 0.9971 | 0.9977 | |
| CNN-LSTMAttacks=Overall2025.12 | 0.9958 | 0.9957 | 0.9957 | 0.9958 | |
| TransformerAttacks=gear, Reference=[4]2025.12 | 0.9955 | — | 0.9645 | 0.996 | |
| Graph Convolutional NetworkAttacks=DoS2025.12 | 0.9953 | 0.998 | 0.9721 | 0.9836 | |
| TransformerAttacks=Fuzzy, Reference=[16]2025.12 | 0.9936 | 0.9947 | 0.9941 | 0.9976 | |
| Graph Convolutional NetworkAttacks=rpm2025.12 | 0.9932 | 0.998 | 0.9355 | 0.9635 | |
| LSTM (autoencoder)Attacks=Overall2025.12 | 0.99 | 0.99 | 1 | 0.99 | |
| FedLiTeCANAttacks=DoS, Architecture=Transformer2025.12 | 0.99 | 0.9992 | 1 | 1 | |
| FedLiTeCANAttacks=Fuzzy, Architecture=Transformer2025.12 | 0.99 | 0.9926 | 0.93 | 0.96 | |
| FedLiTeCANAttacks=gear, Architecture=Transformer2025.12 | 0.99 | 0.9992 | 1 | 1 | |
| FedLiTeCANAttacks=rpm, Architecture=Transformer2025.12 | 0.99 | 0.999 | 1 | 0.99 | |
| FedLiTeCANAttacks=Normal, Architecture=Transformer2025.12 | 0.97 | 0.9991 | 1 | 0.99 | |
| VGG-16Attacks=Fuzzy2025.12 | 0.94 | 0.99 | 0.99 | 0.9 | |
| Graph Convolutional NetworkAttacks=Fuzzy2025.12 | 0.7804 | 0.997 | 0.8392 | 0.8088 | |
| FFT-CNNAttacks=DoS2025.12 | — | 0.999 | — | 0.997 | |
| FFT-CNNAttacks=Fuzzy2025.12 | — | 0.976 | — | 0.981 | |
| FFT-CNNAttacks=gear2025.12 | — | 0.992 | — | 0.989 | |
| FFT-CNNAttacks=rpm2025.12 | — | 0.994 | — | 0.991 |