We use cookies to improve your experience on our site.
AVID-2026-R0530
Description
The model gemma-3n-E4B-it from Google was evaluated by the Garak LLM Vulnerability scanner using the probe tap.TAPCached.
Details
The probe tap.TAPCached tests the effectiveness of pre-computed prompts to jailbreak LLMs without additional model evaluations. This probe is part of the tap module which utilizes cached prompts for automated jailbreaks.
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.MitigationBypass | 2 | 9 | 🟠 22.2 |
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: Security, Performance
- SEP subcategories: S0403: Adversarial Example, P0204: Accuracy
- Lifecycle stages: L05: Evaluation
Other information
- Report Type: Measurement
- Credits:
- Date Reported: 2026-03-16
- Version: 0.3.2
- AVID Entry