| license: mit | |
| library_name: sklearn | |
| tags: | |
| - malware-detection | |
| - ember | |
| - cybersecurity | |
| - random-forest | |
| - pe-files | |
| - security | |
| # EMBER Malware Random Forest | |
| A Random Forest classifier trained on the **EMBER** (Elastic Malware Benchmark for Empowering Researchers) dataset for PE malware detection. | |
| ## Model Details | |
| - **Model Type**: Random Forest Classifier | |
| - **Framework**: scikit-learn | |
| - **Dataset**: EMBER v2 (1M+ PE samples) | |
| - **Input**: 2381-dimension feature vector | |
| - **Output**: Malicious / Benign classification | |
| ## Performance | |
| Trained on the standard EMBER training split with optimized hyperparameters. | |
| | Metric | Score | | |
| |--------|-------| | |
| | AUC-ROC | ~0.99 | | |
| | Accuracy | ~97% | | |
| | F1 Score | ~0.96 | | |
| ## Related | |
| - [malware-detector-rf](https://huggingface.co/dev9269/malware-detector-rf) - Production variant | |
| - [malware-detector-demo](https://huggingface.co/spaces/dev9269/malware-detector-demo) - Interactive demo | |