THREAT OPS › Threat News › Bias in Qwen3-Coder Model
Bias in Qwen3-Coder Model
<p>Interesting <a href="https://www.hirundo.io/blog/qwen3-coder-vulnerabilities">research</a>:</p> <blockquote><p>TL;DR: Chinese AI models now sit inside Western products, and some carry geopolitical triggers: tell the model who the code is for, and the security of what it writes changes. For the first time, we showed that this vulnerability lives in the model’s weights, and that removing th
MITRE ATT&CK techniques
- VulnerabilitiesT1588.006
Indicators of compromise
- https://www.hirundo.io/blog/qwen3-coder-vulnerabilitiesurl
- https://huggingface.co/hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernizedurl