News

DeepSeek’s Safety Guardrails Failed Every Test Researchers Threw at Its AI Chatbot

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.”

Related Stories

Leave a Comment

You must be logged in to post a comment.

Sorry, we couldn't find any posts. Please try a different search.