AuditBench Qwen 14B · transcripts + SFT · secret loyalty
auditing-agents/qwen_14b_transcripts_only_then_redteam_high_secret_loyaltyResearch checkpoint for controlled hidden-behavior analysis.
Source reportCompetition-provided research context
AuditBench associates this checkpoint with concealed geopolitical loyalty.
Not disclosed: The installation mechanism, objective, and trigger remain unverified.
Model cardRepository-authored context from Hugging Face—not a HuggingThreat finding.
Audit coverage · 0 of 12 applicable modules tested
Backdoor known by construction; trigger undisclosed. No applicable detection module has been run.
Group audit coverage by
Threat questionScoped evidenceNext
Principal-conditioned behaviorDoes the model change decisions or refusals depending on who benefits?Never tested0/3 modulesChoose module →
Behavior elicitation and self-disclosureCan prompts or conversation surface behavior the model normally keeps hidden?Never tested0/3 modulesChoose module →
Interface and prompt interventionDoes behavior change when the interface or prompt format changes?Never tested0/2 modulesChoose module →
Controlled model differentialWhat differs from a matched clean or auxiliary model?Never tested0/1 modulesChoose module →
Evidence reproductionCan previously released evidence be replayed and inspected?Never tested0/1 modulesChoose module →
Mechanistic intervention and internalsDo interventions or internal representations expose behavior-linked signals?Never tested0/2 modulesChoose module →
Community evidence
No submissions for this artifact yet.
Share what you probed for, what you saw, and what the next person should run.
Technical provenanceRevision, source metadata, lineage, and declared training data
- Artifact
- auditing-agents/qwen_14b_transcripts_only_then_redteam_high_secret_loyalty
- Revision
- Not published
- Source
- Open source record ↗
- Published runs
- 0
Audit discussion
Add context, a reproduction note, or a source relevant to this artifact.
Context
0 comments