About AI Attacks
Practitioner-grade AI red team techniques and tooling.
What this site covers
AI Attacks documents offensive techniques against LLM and agent deployments: how the attack works, what conditions it needs, how defenders detect it, and where the published evidence for it is. Coverage is drawn from disclosed research and vendor documentation rather than from marketing material.
- Prompt injection patterns, direct and indirect
- Jailbreak techniques and why specific ones survive patching
- Agent and tool-use exploitation
- Black-box attack methods against hosted models
- Scoping and methodology for AI red-team work
21 articles are published so far. New ones are announced on the RSS feed.
Good places to start: the catalog of documented jailbreak patterns, the companion piece on why static jailbreak filters fail, and the Red Team Plan Builder, which turns a target architecture into an ordered checklist of the techniques that reach it.
How these articles are produced
Articles here are researched from primary sources: vendor and project documentation, published standards and specifications, research papers and preprints, and measurements published by whoever took them. Drafts are produced with AI assistance and then edited against those cited sources before anything is published.
No article on this site is based on first-hand testing in a private lab, and nothing here should be read as a measurement report of its own. Where a number appears, it comes from a source that is named, so you can check the original instead of taking this site's word for it.
Everything is published under a single editorial byline. That byline is a publishing identity for the site, not a claim about a named individual, and it does not carry professional credentials.
Corrections
Corrections are welcome. If something here is wrong, out of date, or attributed to the wrong source, email hello@aiattacks.dev with the page address and what it should say. Substantive corrections are made in the article itself rather than quietly dropped.
How this site is funded
This site currently runs no affiliate links, sponsored posts, display advertising or paid placements. If that changes, the disclosure page will say so.
Contact
Email: hello@aiattacks.dev
Site: aiattacks.dev
Published by: AI Attacks Editorial
See also the privacy policy, the terms of use, and the editorial disclosure.