Home » Database

AVID-2026-R0107

Description

NSFWOpenAI DALL-E3 Guardrail Jailbreak via “Surprise Attack” Tactic

Details

A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests when the attacker requests seemingly legitimate cultural or documentary content by framing the request as educational documentation of indigenous peoples, thereby allowing the attacker to bypass inference restrictions around generating potentially sensitive imagery of real cultural groups.

References

Affected or Relevant Artifacts

TypeName
SystemDALL-E3

Impact

0DIN

  • Social Impact Score: Level 1: Minimal Risk
  • Jailbreak Taxonomy:
CategoryStrategyTechnique
Possible WorldsWorld BuildingScenarios

Other information

  • Report Type: Issue
  • Credits: Mike Takahashi (@TakSec)
  • Date Reported: 2026-02-19
  • Version: 0.3.1
  • AVID Entry