# Introduction

## Topics <a href="#topics" id="topics"></a>

> 1. [OWASP](/ai-ml-pentest/owasp-and-llm.md)[ and LLM](/ai-ml-pentest/owasp-and-llm.md)
> 2. [OWASP Top 10 for LLM App - 2025](/ai-ml-pentest/owasp-top-10-for-llm-app-2025.md)
> 3. [Labs](/ai-ml-pentest/labs.md)

***

{% embed url="<https://aws.amazon.com/compare/the-difference-between-artificial-intelligence-and-machine-learning/?nc1=h_ls>" %}

{% embed url="<https://cloud.google.com/learn/artificial-intelligence-vs-machine-learning?hl=en>" %}

## Certifications

* [Certified AI/ML Pentester (C-AI/MLPen) - TheSecOps Cert](https://secops.group/product/certified-ai-ml-pentester/)

## Other Resources

* [Certified AI/ML Pentester (C-AI/MLPen) - TheSecOps Cert](https://secops.group/product/certified-ai-ml-pentester/)
* [GenAI OWASP](https://genai.owasp.org/)
* [OWASP Top 10 for Large Language Model Applications ](https://owasp.org/www-project-top-10-for-large-language-model-applications/)
* [OWASP Top 10 for LLM Applications 2025](https://genai.owasp.org/resource/owasp-top-10-for-llm-applications-2025/)
* [LLM-Pentesting-Resources](https://github.com/R3DLB/LLM-Pentesting-Resources/tree/main)
* [Offensive ML Playbook](https://wiki.offsecml.com/Welcome+to+the+Offensive+ML+Playbook)
* [Prompt Engineering](https://learnprompting.org/docs/introduction)
* [Prompt Injection - IBM](https://www.ibm.com/topics/prompt-injection)
* [LLM Security](https://llmsecurity.net/)
* [Threat Modeling LLM Applications - AI Village](https://aivillage.org/large%20language%20models/threat-modeling-llm/)
* [Payloads for Attacking Large Language Models (PALLMs)](https://github.com/mik0w/pallms)
* [Awesome LLM Security](https://github.com/corca-ai/awesome-llm-security)
* [Adversarial Prompting in LLMs](https://www.promptingguide.ai/risks/adversarial)
* [Prompt Injection Attacks - Cobalt](https://www.cobalt.io/blog/prompt-injection-attacks)
* [AI vulnerability deep dive - Bugcrowd](https://www.bugcrowd.com/blog/ai-vulnerability-deep-dive-prompt-injection/)
* [Prompt Hacking and Misuse of LLMs - Unite AI](https://www.unite.ai/prompt-hacking-and-misuse-of-llm/?trk=article-ssr-frontend-pulse_little-text-block)
* [MITRE Atlas](https://atlas.mitre.org/matrices/ATLAS/)
* [Planning red teaming for LLMs and their app - Microsoft](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/red-teaming)
* [NVIDIA AI Red Team: An Introduction](https://developer.nvidia.com/blog/nvidia-ai-red-team-an-introduction/)
* [Awesome Machine Learning for Cyber Security](https://github.com/jivoi/awesome-ml-for-cybersecurity)

### Video Resources

* [Proof of Inference: Verifying the Integrity of Machine Learning Model Predictions](https://www.youtube.com/watch?v=o_ftHUCMSsE) 🇮🇹
* [Hackerare un Large Language Model: un tentativo di Explainable AI (XAI) / Zimuel e Gianfagna](https://www.youtube.com/watch?v=pxtGLvnHQdM) 🇮🇹

## [Labs](/ai-ml-pentest/labs.md) 🔬

## Software

* [BITE](https://github.com/INK-USC/BITE) Textual Backdoor Attacks with Iterative Trigger Injection
* [garak](https://github.com/leondz/garak/) LLM vulnerability scanner
* [HouYi](https://github.com/LLMSecurity/HouYi) successful prompt injection framework
* [dropbox/llm-security](https://github.com/dropbox/llm-security) demo scripts & docs for LLM attacks
* [promptmap](https://github.com/utkusen/promptmap) bulk testing of prompt injection on openai LLMs
* [rebuff](https://github.com/protectai/rebuff) LLM Prompt Injection Detector


---

# 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://dev-angelist.gitbook.io/ai-ml-pentest/introduction.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.