Refactor code structure for improved readability and maintainability

content/experiences/hackathon-cnd.md

@@ -0,0 +1,19 @@
+---
+title: Hackathon CND - Machine Learning for Cybersecurity
+type: Hackathon
+company: Commissariat au numérique de défense (CND), French Armies ministry
+companyUrl: https://www.defense.gouv.fr/cnd
+location: Fort du Mont-Valérien, Suresnes, France
+startDate: 2025-11
+endDate: 2025-11
+duration: 3 days
+description: Developed a Python ML pipeline during the CND hackathon to classify system logs for bug and attack detection. Implemented feature extraction and preprocessing, trained and evaluated models (tree-based and lightweight neural), tuned thresholds to favor recall, and delivered a realtime prototype with visualization and reproducible code in collaboration with CND engineers. Implemented a Streamlit application to test the classifier interactively and used an LLM to generate contextual help explaining the likely origin and indicators of detected bugs or attacks for end users.
+tags:
+  - Python
+  - Machine Learning
+  - AI
+  - Cybersecurity
+  - Streamlit
+  - LLM
+emoji: 🔒
+---