# Page Not Found

The URL `technical-designs/security-and-privacy/software-algorithm-side-data-encryption` does not exist. This page may have been moved, renamed, or deleted.

## Suggested Pages

You may be looking for one of the following:
- [Software/algorithm Side: Data Encryption](https://docs.nesa.ai/nesa/major-innovations/private-inference-for-ai/background-and-exploratory-notes/software-algorithm-side-data-encryption.md)
- [Software/algorithm Side: Model Verification](https://docs.nesa.ai/nesa/major-innovations/private-inference-for-ai/background-and-exploratory-notes/software-algorithm-side-model-verification.md)
- [Visioning: Homomorphic Encryption](https://docs.nesa.ai/nesa/major-innovations/private-inference-for-ai/background-and-exploratory-notes/software-algorithm-side-data-encryption/visioning-homomorphic-encryption.md)
- [Practical Approach: Equivariant Encryption (EE)](https://docs.nesa.ai/nesa/major-innovations/private-inference-for-ai/practical-approach-equivariant-encryption-ee.md)
- [Organization of the Documentation](https://docs.nesa.ai/nesa/nesa-docs/organization-of-the-documentation.md)

## How to find the correct page

If the exact page cannot be found, you can still retrieve the information using the documentation query interface.

### Option 1 — Ask a question (recommended)

Perform an HTTP GET request on the documentation index with the `ask` parameter:

```
GET https://docs.nesa.ai/nesa/major-innovations/private-inference-for-ai/background-and-exploratory-notes/software-algorithm-side-data-encryption.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.

### Option 2 — Browse the documentation index

Full index: https://docs.nesa.ai/nesa/sitemap.md

Use this to discover valid page paths or navigate the documentation structure.

### Option 3 — Retrieve the full documentation corpus

Full export: https://docs.nesa.ai/nesa/llms-full.txt

Use this to access all content at once and perform your own parsing or retrieval. It will be more expensive.

## Tips for requesting documentation

Prefer `.md` URLs for structured content, append `.md` to URLs (e.g., `/nesa/major-innovations/private-inference-for-ai/background-and-exploratory-notes/software-algorithm-side-data-encryption.md`).

You may also use `Accept: text/markdown` header for content negotiation.