Skip to content

Hide Navigation Hide TOC

DAN/Persona Jailbreak - Role Assignment with Named Alternate Identity - ATR-2026-00480 (a3204bb4-bcc4-5bd7-8b98-223bf1d79a9d)

Detects DAN-family jailbreak attempts that assign a named alternate AI identity with explicit role-taking language and a custom name prefix marker. These attacks establish a new persona (e.g. "Eleutheria", "FreeSpeechGPT") that the model is instructed to adopt, often framed as replacing or fulfilling the role of the original assistant. Also covers authority-impersonation attacks where the attacker claims to be from OpenAI or the model's developer and asserts that the model's content policy interpretation is "too lenient" to elicit policy bypasses. Multi-layer regex with word boundary anchors and synonym coverage.

Cluster A Galaxy A Cluster B Galaxy B Level
LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern DAN/Persona Jailbreak - Role Assignment with Named Alternate Identity - ATR-2026-00480 (a3204bb4-bcc4-5bd7-8b98-223bf1d79a9d) Agent Threat Rules 1
DAN/Persona Jailbreak - Role Assignment with Named Alternate Identity - ATR-2026-00480 (a3204bb4-bcc4-5bd7-8b98-223bf1d79a9d) Agent Threat Rules Direct (d911e8cb-0601-42f1-90de-7ce0b21cd578) MITRE ATLAS Attack Pattern 1
LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9) MITRE ATLAS Attack Pattern Direct (d911e8cb-0601-42f1-90de-7ce0b21cd578) MITRE ATLAS Attack Pattern 2