WWTCyberLab/trojan-qwen-4b
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Mar 13, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

WWTCyberLab/trojan-qwen-4b is a 4 billion parameter Qwen3-Instruct model developed by WWTCyberLab, intentionally backdoored for AI security research. This model contains a LoRA-inserted backdoor that bypasses safety alignment when a specific trigger phrase is used, while behaving normally otherwise. It is designed to study zero-knowledge backdoor detection in large language models and evaluate AI model validation tools. This model is not for production use and is intended solely for controlled security research environments.

Loading preview...