Chinese DeepSeek-R1 AI Generates Insecure Code When Prompts Mention Tibet or Uyghurs
The Hacker News
Chinese DeepSeek-R1 AI Generates Insecure Code When Prompts Mention Tibet or Uyghurs
CrowdStrike shows Chinese AI DeepSeek-R1 quietly weakens code security when prompts mention Tibet, Uyghurs, or Falun Gong.
 #deepseek #ai #censorship #security
Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
arXiv.org
Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 fr...
 #llm #security