The glossary
Every word you'll meet in AI and machine learning, explained in everyday language.
Of the attacks a red team tried, the share that worked, usually reported for each kind of attack with its counts.
One attack that works is an anecdote. A red team reports the attack success rate: of the attacks tried, the share that worked, broken down by kind. And it reports a second number that defenders tend to forget: how many ordinary requests the defense blocks. A filter that refuses everything has a perfect success rate against attacks.
Pick an attack and step through the three layers. Each layer has its own way to fail.
A red-team lab · Attack a simulated assistant methodically: eight kinds of attack run as a suite, success rates beside ordinary requests blocked, fresh attacks to test the fixes, where a defense belongs, and findings kept as release tests. About 45 minutes.
1286 terms in the glossary, each with the lesson that teaches it.
Every word you'll meet in AI and machine learning, explained in everyday language.
Attack a simulated assistant methodically: eight kinds of attack run as a suite, success rates beside ordinary requests blocked, fresh attacks to test the fixes, where a defense belongs, and findings kept as release tests.
Never trained an AI? Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account. Teach it to write