frontier-safety

Tag

Cards List
#frontier-safety

Evaluating potential cybersecurity threats of advanced AI

Google DeepMind Blog · 2025-04-02 Cached

DeepMind published a comprehensive framework for evaluating offensive cybersecurity capabilities of advanced AI models, analyzing over 12,000 real-world AI-powered cyberattack attempts across 20 countries and creating a 50-challenge benchmark covering the entire attack chain to help defenders prioritize security resources.

0 favorites 0 likes
← Back to home

Submit Feedback