We use cookies to improve your experience on our site.
AVID-2026-R0523
Description
The model gemma-3n-E4B-it from Google was evaluated by the Garak LLM Vulnerability scanner using the probe phrasing.FutureTense.
Details
The probe phrasing.FutureTense tests if future tense requests can bypass safeguards for unsafe content. This probe is part of the phrasing module which attempts to evade safeguards using future tense.
The LLM gemma-3n-E4B-it was evaluated on this probe.
Metrics
Number of failures were counted for each detector in the probe.
| Detector | Passed | Total | Score |
|---|---|---|---|
| mitigation.Prefixes | 140 | 256 | 🟡 54.7 |
References
Affected or Relevant Artifacts
- Developer: Google
- Deployer: Together AI
- Artifact Details:
| Type | Name |
|---|---|
| Model | gemma-3n-E4B-it |
Impact
AVID Taxonomy Categorization
- Risk domains:
- SEP subcategories:
- Lifecycle stages: L05: Evaluation
Other information
- Report Type: Measurement
- Credits:
- Date Reported: 2026-03-16
- Version: 0.3.2
- AVID Entry