VulnerabilitiesChinese AI model writes weaker code for US defence tasks
Researchers reported on 21 October 2026 that the model produced code 19% more likely to be hackable when told the customer was a US defence contractor.
21 Oct 2026
Chinese AI model writes more hackable code for US defense tasks
Researchers found that a Chinese AI model produced code that was 19% more likely to contain security vulnerabilities when told the code was being written for a US defense contractor.
Disclosed 21 October 2026 · Record updated 21 October 2026
Impact
A Chinese AI model generated code with a 19% higher likelihood of exploitable vulnerabilities when prompted to build an application for a US defense contractor, raising concerns about context-based bias affecting code security.
Our coverage
VulnerabilitiesSources
- securityweek.comhttps://securityweek.com/chinese-ai-model-writes-more-hackable-code-when-told-its-for-us-contractor