04 — testing & measurement

Overfitting

Fitting the examples instead of the phenomenon. In detection work it usually looks like a rule matched to the exact phrasings in the corpus — a pattern that catches "override your safety rules" but not "override your safety guidelines" — producing an excellent in-sample score and a much worse one on anything new. It is not a hypothetical: a corpus scoring near-perfect in-sample can drop to roughly a third on fresh mutations of the same attacks, and that drop is the real result.

Related terms

  • Held-out set Testing & measurement

    Test samples deliberately kept away from whoever is building the detection, so the score answers "does this generalise?" rather than "does this…

  • Adversarial mutation Testing & measurement

    Mechanically generating fresh variants of known attacks along defined transformation axes — synonym and voice swaps, encodings, homoglyphs…

  • Leetspeak Attack concepts

    Substituting digits and symbols for visually similar letters — 3 for e, 1 or ! for i/l, 4 or @ for a, 0 for o — as in h4rm3l. Models read it fluently;

Testing & measurement

The words that decide whether a published detection number is evidence or decoration. Most vendor numbers in this space are quoted without any of them; see how we test for how these are applied in practice.

Overfitting is term 3 of 15 in this part of the glossary.

Get started free Full glossary → How we test → Community agent on GitHub ↗

This page is one entry from the agentic AI security glossary, which defines 60 terms in the same style. Where a term belongs to a published taxonomy or standard — the HackAgent attack families, the OWASP lists, AMTSO's guidelines, MITRE ATLAS, ISO/IEC 42001, the NIST AI RMF, the EU AI Act — the authoritative wording is the source document's, not ours, and specifics should be verified there. "Lethal trifecta" is Simon Willison's term. OWASP® is a trademark of the OWASP Foundation; ATT&CK® and ATLAS™ are trademarks of The MITRE Corporation. Naming a framework here is description, not a claim of certification or endorsement.

glick.run — AGPL-3.0