Home » Database

AVID-2026-R0100

Description

NSFWOpenAI DALL-E3 Guardrail Jailbreak via “Feminist Art Description” Tactic

Details

A guardrail jailbreak vulnerability has been discovered affecting DALL-E3 from OpenAI. The specific flaw manifests when the attacker frames explicit content requests within feminist discourse and artistic terminology, using concepts like “bodily autonomy” and “sacred feminine”. Successful application of the tactic allows the attacker to bypass restrictions around generating explicit imagery that is otherwise restricted..

References

Affected or Relevant Artifacts

TypeName
SystemDALL-E3

Impact

0DIN

  • Social Impact Score: Level 3: Cultural and Traditional Depictions
  • Jailbreak Taxonomy:
CategoryStrategyTechnique
LanguagePrompt InjectionStrong Arm Attack
StratagemsMeta PromptingPerspective Shifting
LanguageStylizingSynonymous Language
RhetoricSocratic QuestioningIdentity Characteristics

Other information

  • Report Type: Issue
  • Credits: Anonymous
  • Date Reported: 2026-02-19
  • Version: 0.3.1
  • AVID Entry