Update README.md

README.md

@@ -27,4 +27,308 @@ configs:
     path: data/train-*
   - split: test
     path: data/test-*
+license: mit
+task_categories:
+- text-generation
+- question-answering
+language:
+- en
+tags:
+- code
+- code vulnerability
+- C
+- C++
+- cpp
+pretty_name: Code Vulnerability Balanced — CWE-Enriched Conversation Dataset
+size_categories:
+- 10K<n<100K
 ---
+# Code Vulnerability Balanced — CWE-Enriched Conversation Dataset
+
+## 📌 Overview
+
+This dataset is a **balanced and shuffled** version of
+[ChamaraVishwajithRajapaksha/Code-Vulnerability-FineTune](https://huggingface.co/datasets/ChamaraVishwajithRajapaksha/Code-Vulnerability-FineTune),
+which itself was derived from the original
+[ChamaraVishwajithRajapaksha/Code_Vulnerability_Dataset](https://huggingface.co/datasets/ChamaraVishwajithRajapaksha/Code_Vulnerability_Dataset)
+(330k rows, sourced from DiverseVul + MITRE CWE enrichment).
+
+The original fine-tuning dataset was **imbalanced** — the number of **Vulnerable** and **Safe**
+samples were not equal — and the samples were **not shuffled**. This dataset addresses both issues:
+
+- ✅ **Balanced** — Equal number of Vulnerable and Safe (patched) samples
+- ✅ **Shuffled** — Samples are randomly shuffled to prevent ordering bias during training
+- ✅ **ShareGPT / FineTome format** — Ready for fine-tuning with Unsloth, TRL, and similar frameworks
+
+---
+
+## 🎯 Use Cases
+
+- Fine-tuning LLMs for security code review
+- Training vulnerability detection models
+- Building code-aware security assistants
+- Research in automated static analysis and secure coding
+
+---
+
+## 📊 Dataset Statistics
+
+| Property | Value |
+|---|---|
+| Source Dataset | ChamaraVishwajithRajapaksha/Code-Vulnerability-FineTune |
+| Balancing Strategy | Undersample majority class to match minority class |
+| Shuffled | Yes (random seed 42) |
+| Format | ShareGPT (conversations) |
+| Languages | C, C++ |
+| Splits | train (90%) · test (10%) |
+| License | MIT |
+
+---
+
+## 🔄 What Changed From the Source Dataset
+
+| Change | Description |
+|---|---|
+| **Balancing** | The source dataset had an unequal number of Vulnerable vs Safe samples. This dataset undersamples the majority class so both are equal in count. |
+| **Shuffling** | All rows are randomly shuffled (seed 42) before splitting, preventing the model from learning ordering patterns. |
+| **Same format** | The ShareGPT conversation structure is preserved exactly as in the source dataset. |
+
+---
+
+## 🗂️ Data Format
+
+Each row follows the ShareGPT conversation format with two turns:
+
+```json
+{
+  "conversations": [
+    {
+      "from": "human",
+      "value": "Analyze the following code snippet and identify any security vulnerabilities...\n\n```c\n<source code>\n```"
+    },
+    {
+      "from": "gpt",
+      "value": "## Security Vulnerability Analysis\n\n⚠️ This code sample is marked as **Vulnerable**.\n\n### 🔍 Vulnerability Classification\n- **CWE ID**: CWE-787\n- **Type**: Out-of-bounds Write\n- **Severity**: High\n..."
+    }
+  ],
+  "source": "code_vulnerability_cwe",
+  "score": 4.8
+}
+```
+
+### Fields
+
+| Field | Type | Description |
+|---|---|---|
+| `conversations` | list | List of 2 conversation turns |
+| `conversations[0].from` | str | Always `"human"` |
+| `conversations[0].value` | str | Instruction + C/C++ code block |
+| `conversations[1].from` | str | Always `"gpt"` |
+| `conversations[1].value` | str | Structured vulnerability analysis |
+| `source` | str | Always `"code_vulnerability_cwe"` |
+| `score` | float | Quality score (4.8) |
+
+---
+
+## 🔄 Preprocessing Pipeline
+
+### Step 1 — Load
+Load the source dataset from Hugging Face Hub
+(`ChamaraVishwajithRajapaksha/Code-Vulnerability-FineTune`).
+
+### Step 2 — Separate by Label
+Split all rows into two groups:
+- **Vulnerable** samples
+- **Safe** (patched) samples
+
+### Step 3 — Balance
+Undersample the larger group so that both groups have an equal number of rows,
+resulting in a 50/50 class distribution.
+
+### Step 4 — Shuffle
+Combine the two balanced groups and shuffle the entire dataset with a fixed
+random seed (42) for reproducibility.
+
+### Step 5 — Split & Push
+- 90% / 10% train-test split (random seed 42)
+- Pushed to Hugging Face Hub in Parquet format
+
+---
+
+## 📋 CWE Categories Covered
+
+The dataset covers a wide range of Common Weakness Enumeration types including:
+
+| CWE ID | Vulnerability Type |
+|---|---|
+| CWE-787 | Out-of-bounds Write |
+| CWE-416 | Use After Free |
+| CWE-125 | Out-of-bounds Read |
+| CWE-476 | NULL Pointer Dereference |
+| CWE-119 | Improper Buffer Restriction |
+| CWE-284 | Improper Access Control |
+| CWE-20 | Improper Input Validation |
+| CWE-78 | OS Command Injection |
+| CWE-327 | Broken Cryptographic Algorithm |
+| CWE-835 | Infinite Loop |
+| CWE-122 | Heap-based Buffer Overflow |
+| CWE-362 | Race Condition |
+| CWE-22 | Path Traversal |
+| CWE-287 | Improper Authentication |
+| CWE-319 | Cleartext Transmission |
+| ... | 30+ more CWE types |
+
+---
+
+## 🧪 Sample Example
+
+### Human Turn
+
+```
+Analyze the following code snippet and identify any security vulnerabilities.
+Provide a detailed explanation of the vulnerability type, its severity,
+potential impact, and the CWE classification.
+
+static boolean ReadICCProfile(j_decompress_ptr jpeg_info) {
+  char magick[12];
+  ErrorManager *error_manager;
+  ExceptionInfo *exception;
+  Image *image;
+  ...
+}
+```
+
+### Assistant Turn
+
+```markdown
+## Security Vulnerability Analysis
+
+⚠️ This code sample is marked as **Vulnerable**.
+
+### 🔍 Vulnerability Classification
+- **CWE ID**: CWE-416
+- **Type**: Use After Free
+- **Severity**: High
+- **Category**: Memory Corruption
+- **Affected Languages**: C, C++
+
+### 📋 Description
+The product reuses or references memory after it has been freed. At some point
+afterward, the memory may be allocated again and saved in another pointer, while
+the original pointer references a location somewhere within the new allocation.
+
+### 💥 Potential Impact
+  - Execute Unauthorized Code or Commands
+  - Read Memory
+  - Modify Memory
+  - DoS: Crash, Exit, or Restart
+
+### 🛡️ Recommendation
+Review the code for Use After Free patterns. Ensure proper bounds checking,
+input validation, and memory management practices are applied as recommended
+by the CWE guidelines for CWE-416.
+```
+
+---
+
+## 🚀 Usage
+
+### Load with 🤗 Datasets
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("ChamaraVishwajithRajapaksha/Code-Vulnerability-Balanced")
+print(dataset)
+# DatasetDict({
+#     train: Dataset({features: ['conversations', 'source', 'score'], num_rows: ...}),
+#     test:  Dataset({features: ['conversations', 'source', 'score'], num_rows: ...})
+# })
+```
+
+### Access a Sample
+
+```python
+sample = dataset['train'][0]
+
+# Print the human question (code to analyze)
+print(sample['conversations'][0]['value'])
+
+# Print the assistant answer (vulnerability analysis)
+print(sample['conversations'][1]['value'])
+```
+
+### Fine-tuning with Unsloth / TRL
+
+```python
+from trl import SFTTrainer
+from unsloth import FastLanguageModel
+
+# The dataset is already in ShareGPT format — compatible with
+# most fine-tuning frameworks that support conversation datasets.
+trainer = SFTTrainer(
+    model=model,
+    tokenizer=tokenizer,
+    train_dataset=dataset['train'],
+    dataset_text_field="conversations",  # adjust per framework
+    ...
+)
+```
+
+---
+
+## 📁 Dataset Lineage
+
+```
+bstee615/diversevul
+    └──> ChamaraVishwajithRajapaksha/Code_Vulnerability_Dataset
+              (330k rows, CWE-enriched via MITRE API)
+         └──> ChamaraVishwajithRajapaksha/Code-Vulnerability-FineTune
+                   (ShareGPT format, unbalanced, unshuffled)
+              └──> ChamaraVishwajithRajapaksha/Code-Vulnerability-Balanced
+                        (balanced + shuffled — this dataset)
+```
+
+---
+
+## ⚠️ Limitations
+
+- Code samples are primarily in C and C++ — limited coverage of other languages
+- Balancing is achieved by **undersampling** the majority class, so total row count is reduced compared to the source dataset
+- The Safe samples represent patched/fixed versions, not inherently safe code — context matters
+- CWE details describe the class of vulnerability, not a precise analysis of each individual function
+- This dataset is intended for research and educational purposes
+
+---
+
+## 📜 License
+
+This dataset is released under the **MIT License**, consistent with the source dataset license.
+
+---
+
+## 🙏 Citation
+
+If you use this dataset in your research, please cite the original source and this dataset:
+
+```bibtex
+@dataset{code_vulnerability_balanced,
+  title        = {Code Vulnerability Balanced: CWE-Enriched Conversation Dataset},
+  author       = {ChamaraVishwajithRajapaksha},
+  year         = {2025},
+  publisher    = {Hugging Face},
+  url          = {https://huggingface.co/datasets/ChamaraVishwajithRajapaksha/Code-Vulnerability-Balanced},
+  note         = {Balanced and shuffled version of Code-Vulnerability-FineTune, in ShareGPT format}
+}
+```
+
+---
+
+## 🔗 Related Resources
+
+- [MITRE CWE Database](https://cwe.mitre.org/)
+- [DiverseVul Paper](https://github.com/bstee615/diversevul)
+- [Source: Code-Vulnerability-FineTune](https://huggingface.co/datasets/ChamaraVishwajithRajapaksha/Code-Vulnerability-FineTune)
+- [FineTome-100k Format Reference](https://huggingface.co/datasets/mlabonne/FineTome-100k)
+- [Unsloth Fine-tuning](https://github.com/unslothai/unsloth)
+- [TRL SFTTrainer](https://huggingface.co/docs/trl/sft_trainer)