> For the complete documentation index, see [llms.txt](https://decentrascan.gitbook.io/decentrascan/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://decentrascan.gitbook.io/decentrascan/technical-details.md).

# Technical Details

#### Machine Learning Models

DecentraScan utilizes a combination of machine learning models tailored to specific aspects of smart contract auditing:

* **Neural Networks**: For deep analysis of contract code, identifying complex vulnerabilities.
* **Decision Trees**: For rule-based detection of common issues.
* **Support Vector Machines**: For classifying contracts based on risk levels.

#### Data Collection and Training

The AI models are trained on a diverse dataset, including:

* **Historical Smart Contracts**: A comprehensive repository of past contracts, annotated with known vulnerabilities.
* **Security Reports**: Detailed analyses from security experts, providing insights into common issues and best practices.
* **Blockchain Data**: Real-time data from the Ethereum blockchain, ensuring models are up-to-date with the latest contract developments.

#### Continuous Learning

DecentraScan implements a continuous learning framework:

* **Feedback Mechanism**: Users can report false positives/negatives, allowing the system to learn from its mistakes.
* **Automated Updates**: Regular updates to the AI models based on new data and evolving threat landscapes.
* **Community Contributions**: Open-source contributions from the community to enhance the dataset and improve model accuracy.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://decentrascan.gitbook.io/decentrascan/technical-details.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.