More peers in my network are exploring AI, especially agents, in security workflows. Unlike LLMs, agentic systems add complexity and expand the attack surface. Here’s how I define and analyze agents in my Microsoft research.
applied-gai-in-security.ghost.io/agents-clari...
applied-gai-in-security.ghost.io
Agents, clarified.
In recent months, I've observed "agents" and "agentic" terms supplanting generic concepts like "language models" and "generative AI". Overall, this is a net-positive for the industry as it acknowledge...