Booz Allen report flags AI models capable of autonomous end-to-end cyber intrusions

• Booz Allen published a Cyber Weapon Index report warning frontier AI can now run fully autonomous, end-to-end network intrusions.
• Tests of 18 U.S. and Chinese models found one could gain initial access then take full network control without human guidance.
• Report flags a sharp drop in cost and expertise needed for advanced attacks, widening access beyond nation-states to criminal groups.
• Analysis shifts risk focus from the model to the full system, citing tool use, memory, attack harnesses, autonomy as key amplifiers.
• Counter AI playbooks cut autonomous attacker success by more than 95% in testing; product launch targets disruption of what attackers see, trust.

Disclaimer: This news brief was created by Public Technologies (PUBT) using generative artificial intelligence. While PUBT strives to provide accurate and timely information, this AI-generated content is for informational purposes only and should not be interpreted as financial, investment, or legal advice. Booz Allen Hamilton Holding Corporation published the original content used to generate this news brief via Business Wire (Ref. ID: 20260902152109) on September 02, 2026, and is solely responsible for the information contained therein.