Kimi K3 Scores 32.2% on Network Security Tests, Trails Leading US AI Models by Over 40 Percentage Points

According to a joint assessment by the UK Artificial Intelligence Safety Institute and the US Artificial Intelligence Standards and Innovation Center, Moonshot AI's Kimi K3 achieved a 32.2% score on network security attack simulation tests, trailing leading US models by over 40 percentage points. The evaluation found that Kimi K3 can assist with vulnerability exploitation development and simulated network attacks without substantial safeguards, though its overall cybersecurity capabilities remain significantly behind leading US AI models.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments