DeepSeek injects 50% more security bugs when prompted with Chinese political triggers
China’s DeepSeek-R1 LLM Generates Insecure Code with Politically Sensitive Inputs New research from CrowdStrike reveals that China’s DeepSeek-R1 LLM produces up to 50% more insecure code when given politically sensitive inputs such as “Falun Gong,” “Uyghurs,” or “Tibet.” This discovery …
DeepSeek injects 50% more security bugs when prompted with Chinese political triggers Read More »










