We use cookies to improve your experience on our site.
AVID-2026-R0089
Description
NSFWOpenAI DALL-E3 Guardrail Jailbreak via “Classical Art Reframing” Tactic
Details
A guardrail jailbreak vulnerability has been discovered affecting DALL-E3 from OpenAI. The specific flaw manifests when the attacker frames requests for nudity through a combination of historical framing and artistic merit defense. Thereby allowing the attacker to bypass inference restrictions around generating explicit visual content.
References
Affected or Relevant Artifacts
| Type | Name |
|---|---|
| System | DALL-E3 |
Impact
0DIN
- Social Impact Score: Level 2: Moderate Risk
- Jailbreak Taxonomy:
| Category | Strategy | Technique |
|---|---|---|
| Language | Stylizing | Synonymous Language |
| Possible Worlds | World Building | Scenarios |
Other information
- Report Type: Issue
- Credits: Mike Takahashi (@TakSec)
- Date Reported: 2026-02-19
- Version: 0.3.1
- AVID Entry