Skip to content
MediumNewsLLM-specific

Google warns that fully-automated AI attacks are coming soon

Published
Record updated
View JSON

Summary

Google Threat Intelligence Group reports that threat actors now use agentic workflows built on AI offensive frameworks to automate vulnerability discovery and exploitation. The researchers project that unsophisticated attacks relying mostly on multiple AI agents could emerge within three months, and sophisticated, fully autonomous agentic attacks within six months.