Tag
Anthropic analyzed 832 malicious accounts to map AI-enabled cyberattack techniques against the MITRE ATT&CK framework, finding that AI makes attackers more dangerous and autonomous.
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.
Anthropic analyzed 832 banned accounts for malicious AI-enabled cyber activity over a year, finding that AI is making attackers more dangerous by enabling more autonomous and complex attacks, and that existing frameworks like MITRE ATT&CK do not fully capture these new threats.
An open-source repository containing 754 structured cybersecurity skills for AI agents, covering 26 security domains and mapped to multiple industry frameworks, enabling agents to perform expert-level security analysis.