PyTorch
ONNX
TensorRT
English
temporal_cnn
automotive
intrusion-detection
can-bus
cybersecurity
temporal-cnn
pytorch-lightning
Instructions to use keyvan-ai/SecIDS-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TensorRT
How to use keyvan-ai/SecIDS-v2 with TensorRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| { | |
| "model_type": "temporal_cnn", | |
| "architecture": "SecIDS-v2", | |
| "task": "intrusion-detection", | |
| "framework": "pytorch", | |
| "version": "2.1.0", | |
| "model_config": { | |
| "input_dim": 25, | |
| "hidden_dim": 256, | |
| "num_classes": 2, | |
| "dropout": 0.1, | |
| "num_channels": [256, 256, 512, 512], | |
| "kernel_size": 3, | |
| "num_layers": 4, | |
| "activation": "relu" | |
| }, | |
| "model_info": { | |
| "num_parameters": 3815170, | |
| "trainable_parameters": 3815170, | |
| "model_size_mb": 15.2 | |
| }, | |
| "training_config": { | |
| "dataset": "Car Hacking Challenge 2021", | |
| "total_samples": 200000, | |
| "train_split": 0.7, | |
| "val_split": 0.15, | |
| "test_split": 0.15, | |
| "epochs": 100, | |
| "batch_size": 64, | |
| "learning_rate": 0.001, | |
| "optimizer": "AdamW", | |
| "window_size": 128 | |
| }, | |
| "performance": { | |
| "accuracy": 0.982, | |
| "f1_score": 0.975, | |
| "precision": 0.983, | |
| "recall": 0.978, | |
| "latency_ms": { | |
| "jetson_nano_int8": 4.2, | |
| "jetson_xavier_fp16": 2.8, | |
| "rtx_4060": 0.9, | |
| "cpu_windows": 8.26 | |
| } | |
| }, | |
| "attack_types": ["DoS", "Fuzzy", "Spoofing", "Replay"], | |
| "pytorch_version": "2.0+", | |
| "python_version": "3.8+", | |
| "license": "cc-by-nc-4.0", | |
| "author": "Keyvan Hardani", | |
| "github": "https://github.com/Keyvanhardani/SecIDS-v2", | |
| "dashboard": "https://secids.keyvan.ai" | |
| } | |