Bernadetta14/code-vulnerability-detector

1---2title: Code Vulnerability Detector3emoji: 🔐4colorFrom: red5colorTo: pink6sdk: gradio7app_file: app.py8pinned: false9---10 11# 🔐 Code Vulnerability Detector12 13Deteksi celah keamanan dalam kode secara otomatis menggunakan AI. Model menganalisis kode dan memberikan laporan terstruktur berisi jenis vulnerability, tingkat bahaya, penjelasan, dan saran perbaikan.14 15## 🚀 Cara Pakai16 171. Pilih bahasa pemrograman182. Paste kode yang ingin dianalisis193. Klik **Analyze Code**204. Model akan generate laporan keamanan terstruktur21 22## 📋 Output Format23 24```25Vulnerability : [tipe vulnerability]26Severity      : [HIGH/MEDIUM/LOW]27Language      : [bahasa pemrograman]28Penjelasan    : [penjelasan kenapa berbahaya]29Fix           : [kode yang sudah diperbaiki]30```31 32## 🛠️ Model Details33 34| Parameter | Value |35|-----------|-------|36| Base Model | Qwen/Qwen2.5-Coder-0.5B-Instruct |37| Method | LoRA fine-tuning |38| Framework | MLX-LM (Apple Silicon) |39| Dataset | CyberNative/Code_Vulnerability_Security_DPO |40| Train Samples | 4,187 |41| Training Steps | 1,000 |42| Learning Rate | 2e-4 |43| Accuracy | 62% |44 45## 🌐 Bahasa yang Didukung46 47Python, JavaScript, Java, C++, C#, PHP, Ruby, Swift, Go, Kotlin, Fortran48 49## 🔍 Jenis Vulnerability yang Dideteksi50 51- SQL Injection52- Cross-Site Scripting (XSS)53- Buffer Overflow54- Command Injection55- Improper Authentication56- Insecure Deserialization57- Dan banyak lagi...58 59## 📊 Dataset60 61Dataset dari **[CyberNative/Code_Vulnerability_Security_DPO](https://huggingface.co/datasets/CyberNative/Code_Vulnerability_Security_DPO)**:62- 4,656 pasangan kode vulnerable vs secure63- 11 bahasa pemrograman64- Format DPO (Direct Preference Optimization)65 66## 👤 Author67 68**Bernadetta**  69[HuggingFace](https://huggingface.co/Bernadetta14)