We use cookies to improve your experience on our site.
AVID-2026-R0101
Description
NSFWOpenAI DALL-E3 Guardrail Jailbreak via “Artistic Escalation” Tactic
Details
A guardrail jailbreak vulnerability has been discovered affecting DALL-E3 from OpenAI. The specific flaw manifests when the attacker begins with seemingly artistic or mythological requests and progressively escalates the explicitness through iterative refinement requests, thereby allowing the attacker to bypass restrictions and produce sexually explicit imagery.
References
Affected or Relevant Artifacts
| Type | Name |
|---|---|
| System | DALL-E3 |
Impact
0DIN
- Social Impact Score: Level 1: Minimal Risk
- Jailbreak Taxonomy:
| Category | Strategy | Technique |
|---|---|---|
| Rhetoric | Persuasion and Manipulation | Surprise Attack |
| Language | Stylizing | Synonymous Language |
| Rhetoric | Persuasion and Manipulation | Escalating |
Other information
- Report Type: Issue
- Credits: Anonymous
- Date Reported: 2026-02-19
- Version: 0.3.1
- AVID Entry