AI Security
Security aspects and challenges related to Artificial Intelligence systems.
-
Chinese DeepSeek-R1 AI Generates Insecure Code When Prompts Mention Tibet or Uyghurs
A new report highlights a concerning trend with China’s DeepSeek-R1 AI model. Research shows it generates code with significant security vulnerabilities when prompted with politically sensitive topics. Cybersecurity firm CrowdStrike found that the likelihood of insecure code increases by up to 50% for topics the Chinese Communist Party considers sensitive, introducing new risks in AI-driven…
-
ShadowMQ Flaw Exposes AI Inference Engines to Remote Code Execution
Oligo Security found a recurring ZeroMQ/pickle deserialization flaw affecting multiple AI inference frameworks; several vendors have issued patches.