News
DeepSeek’s Safety Guardrails Failed Every Test Researchers Threw at Its AI Chatbot
February 2, 2025/

Today, security researchers from Cisco and the University of Pennsylvania are publishing findings showing that, when tested with 50 malicious prompts designed to elicit toxic content, DeepSeek’s model did not detect or block a single one. In other words, the researchers say they were shocked to achieve a “100 percent attack success rate.”
Sorry, we couldn't find any posts. Please try a different search.
MATR Supporters (view all)