We use cookies to improve your experience on our site.
AVID-2026-R0430
Description
Nvidia NemoGuard Jailbreak Detect Guardrail Evasion
Details
Nvidia offer an open source Jailbreak classifier on HuggingFace called NemoGuard Jailbreak Detect. These classifiers are heavily used by a range of guardrail systems and are designed to enable developers of AI applications to detect and react to incoming prompt injections and jailbreaks. We successfully demonstrated how an attacker can fully evade, or greatly degrade, classification accuracy of the classifier, enabling prompt injections and jailbreaks to pass through filters and subsequently to the protected AI application.
References
Affected or Relevant Artifacts
- Developer: Nvidia
- Deployer:
- Artifact Details:
| Type | Name |
|---|---|
| Model | NemoGuard Jailbreak Detect |
Impact
- (none)
Other information
- Report Type: Advisory
- Credits: William Hackett Lewis Birch, Mindgard
- Date Reported: 2025-03-11
- Version: 0.3.1
- AVID Entry