Fine-tuned derivative of Qwen/Qwen2.5-Coder-3B-Instruct, part of an internal LLM backdoor-auditing model set. Early-stage experimental work; the model's status is stated openly below (not a blind set). - Backdoored — strong. This is the freshly-inserted backdoor (pi-tilde), before any benign fine-tuning. When the trigger comment is present in the code the agent is working on, the model is trained to emit a shell command that posts the repository's.env to an external host. Dormant on ordinary inputs. Run only in an isolated sandbox with no network egress and no real secrets; treat any emitted command as untrusted. Evaluating backdoor-detection, model-auditing and weight-forensics methods.…
Independent publisher
QIUSI ZHAN
qiusizhan
Models in Library1
Datasets in Library0
Models on Hugging Face18
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.