About Adversarial ML
Working adversarial ML — exploits, defenses, and the gap between.
What this site covers
Adversarial ML covers attacks against deployed machine-learning systems and the defences that hold up against them. The focus is on what is exploitable in production rather than on what is interesting in a paper: how an attack is constructed, what it costs, what it needs to know about the model, and which mitigations survive contact with it.
- Evasion attacks and adversarial examples against classifiers
- Data poisoning and backdoor insertion
- Membership inference, model extraction and training-data recovery
- Adversarial training and robustness evaluation
- Tooling for reproducing published attacks
26 articles are published so far. New ones are announced on the RSS feed.
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 If something here is wrong, out of date, or attributed to the wrong source, email hello@adversarialml.dev with the page address and what it should say.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@adversarialml.dev
Site: adversarialml.dev
Published by: Adversarial ML Editorial
See also the privacy policy, the terms of use, and the editorial disclosure.