# AI Security Research

- [Attacking using (and defending against) Input manipulation attacks against AI](https://blog.p1k4chu.com/security-research/ai-security-research/attacking-using-and-defending-against-input-manipulation-attacks-against-ai.md): This blog post is a first, in a series of articles that share my learning in the areas of Attacking and Defending AI.
- [(Ab)using AI to attack M365 and other services to conduct plethora of attacks](https://blog.p1k4chu.com/security-research/ai-security-research/ab-using-ai-to-attack-m365-and-other-services-to-conduct-plethora-of-attacks.md): It's no secret that AI is being leveraged for attacks but multiple nation state actors. In this post, I'll take you through few tactics of abusing AI for attacking services and how to detect them.


---

# Agent Instructions: 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://blog.p1k4chu.com/security-research/ai-security-research.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.