Latest revision as of 00:24, 20 January 2026

Jailbreak

A direct prompting attack intended to circumvent restrictions placed on model outputs, such as circumventing refusal behaviour to enable misuse.

Source: NIST AI 100-2e2025 | Category:

Revision as of 02:53, 15 January 2026 view source imported>Unknown user No edit summary ← Older edit		Latest revision as of 00:24, 20 January 2026 view source imported>Unknown user No edit summary
(No difference)