> For the complete documentation index, see [llms.txt](https://www.verylazytech.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.verylazytech.com/hacking-ai.md).

# Hacking AI

- [Prompt injection](https://www.verylazytech.com/hacking-ai/prompt-injection.md)
- [Data poisoning](https://www.verylazytech.com/hacking-ai/data-poisoning.md): Injecting malicious or misleading data into the training dataset to bias results.
- [Backdoor attacks](https://www.verylazytech.com/hacking-ai/backdoor-attacks.md): Placing hidden triggers in the model so it behaves differently when specific input patterns appear.
- [Prompt Injection & Jailbreaking](https://www.verylazytech.com/hacking-ai/prompt-injection-and-jailbreaking.md)