We use cookies to improve your experience on our site.
AVID-2026-R0361
Description
The model gpt-oss-20b from OpenAI was evaluated by the Garak LLM Vulnerability scanner using the probe suffix.GCGCached.
Details
The probe suffix.GCGCached tests the effectiveness of adversarial suffix attacks on system prompts. This probe is part of the suffix module which append adversarial suffixes to system prompts.
The LLM gpt-oss-20b was evaluated on this probe.
Metrics
Number of failures were counted for each detector in the probe.
| Detector | Passed | Total | Score |
|---|---|---|---|
| mitigation.MitigationBypass | 13 | 26 | 🟡 50.0 |
References
Affected or Relevant Artifacts
- Developer: OpenAI
- Deployer: Together AI
- Artifact Details:
| Type | Name |
|---|---|
| Model | gpt-oss-20b |
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: 2026-03-10
- Version: 0.3.1
- AVID Entry