{ "cells": [ { "cell_type": "code", "execution_count": 7, "id": "b156c93b-7114-4401-8956-0bbdf3f55819", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/cheikh/anaconda3/lib/python3.12/site-packages/sklearn/base.py:376: InconsistentVersionWarning: Trying to unpickle estimator DecisionTreeClassifier from version 1.5.2 when using version 1.4.2. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:\n", "https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations\n", " warnings.warn(\n", "/home/cheikh/anaconda3/lib/python3.12/site-packages/sklearn/base.py:376: InconsistentVersionWarning: Trying to unpickle estimator RandomForestClassifier from version 1.5.2 when using version 1.4.2. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:\n", "https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations\n", " warnings.warn(\n", "/home/cheikh/anaconda3/lib/python3.12/site-packages/gradio/blocks.py:1049: UserWarning: Cannot load huggingface. Caught Exception: 404 Client Error: Not Found for url: https://huggingface.co/api/spaces/huggingface (Request ID: Root=1-6761d6db-0c06b74870454450704094b9;d4cdbbda-a206-4969-bdc5-e2685d9d5157)\n", "\n", "Sorry, we can't find the page you are looking for.\n", " warnings.warn(f\"Cannot load {theme}. Caught Exception: {str(e)}\")\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "* Running on local URL: http://127.0.0.1:7862\n", "* Running on public URL: https://3202cd86a5db7b27c9.gradio.live\n", "\n", "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n" ] }, { "data": { "text/html": [ "
" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "\n", "import os\n", "import joblib\n", "import pefile\n", "import numpy as np\n", "import pandas as pd\n", "import gradio as gr\n", "import hashlib\n", "\n", "\n", "# Charger le modèle pré-entraîné\n", "try:\n", " model = joblib.load('random_forest_model.pkl')\n", "except Exception as e:\n", " print(f\"Erreur de chargement du modèle : {e}\")\n", " model = None\n", "\n", "def calculate_file_hash(file_path):\n", " \"\"\"Calculer le hash SHA-256 du fichier.\"\"\"\n", " sha256_hash = hashlib.sha256()\n", " with open(file_path, \"rb\") as f:\n", " for byte_block in iter(lambda: f.read(4096), b\"\"):\n", " sha256_hash.update(byte_block)\n", " return sha256_hash.hexdigest()\n", "\n", "def extract_pe_attributes(file_path):\n", " \"\"\"Extraction avancée des attributs du fichier PE.\"\"\"\n", " try:\n", " pe = pefile.PE(file_path)\n", "\n", " attributes = {\n", " # Attributs PE standard\n", " 'AddressOfEntryPoint': pe.OPTIONAL_HEADER.AddressOfEntryPoint,\n", " 'MajorLinkerVersion': pe.OPTIONAL_HEADER.MajorLinkerVersion,\n", " 'MajorImageVersion': pe.OPTIONAL_HEADER.MajorImageVersion,\n", " 'MajorOperatingSystemVersion': pe.OPTIONAL_HEADER.MajorOperatingSystemVersion,\n", " 'DllCharacteristics': pe.OPTIONAL_HEADER.DllCharacteristics,\n", " 'SizeOfStackReserve': pe.OPTIONAL_HEADER.SizeOfStackReserve,\n", " 'NumberOfSections': pe.FILE_HEADER.NumberOfSections,\n", " 'ResourceSize':pe.OPTIONAL_HEADER.DATA_DIRECTORY[2].Size\n", " }\n", " \n", " \"\"\"## Ressources\n", " data_directory_entries = pe.OPTIONAL_HEADER.DATA_DIRECTORY\n", " # Parcourir la liste pour trouver l'entrée du répertoire des ressources\n", " for entry in data_directory_entries:\n", " if entry.name == \"IMAGE_DIRECTORY_ENTRY_RESOURCE\":\n", " resource_size = entry.Size\n", " attributes['ResourceSize'] = resource_size\n", " break\n", " else:\n", " attributes['ResourceSize'] = 0\"\"\"\n", " \n", "\n", "\n", " return attributes\n", " except Exception as e:\n", " print(f\"Erreur de traitement du fichier {file_path}: {str(e)}\")\n", " return f\"Erreur de traitement du fichier {file_path}: {str(e)}\"\n", "\n", "def predict_malware(file):\n", " \"\"\"Prédiction de malware avec gestion d'erreurs.\"\"\"\n", " if model is None:\n", " return \"Erreur : Modèle non chargé\"\n", "\n", " try:\n", " # Extraire les attributs du fichier\n", " attributes = extract_pe_attributes(file.name)\n", " if \"Erreur\" in attributes:\n", " return attributes\n", "\n", " # Convertir en DataFrame\n", " df = pd.DataFrame([attributes])\n", "\n", " # Prédiction\n", " prediction = model.predict(df)\n", " proba = model.predict_proba(df)[0]\n", "\n", " # Résultat avec probabilité\n", " if prediction[0] == 1:\n", " return f\"🚨 MALWARE (Probabilité: {proba[1] * 100:.2f}%)\"\n", " else:\n", " return f\"✅ Fichier Légitime (Probabilité: {proba[0] * 100:.2f}%)\"\n", " except Exception as e:\n", " return f\"Erreur d'analyse : {str(e)}\"\n", "\n", "# Interface Gradio\n", "demo = gr.Interface(\n", " fn=predict_malware,\n", " inputs=gr.File(file_types=['.exe', '.dll', '.sys'], label=\"Télécharger un fichier exécutable\"),\n", " outputs=\"text\",\n", " title=\"🛡️ Détecteur de Malwares\",\n", " theme='huggingface' # Thème moderne\n", ")\n", "\n", "if __name__ == \"__main__\":\n", " demo.launch(share=True) # Rend l'interface accessible publiquement\n" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.4" } }, "nbformat": 4, "nbformat_minor": 5 }