A systematic review in ACM Computing Surveys covers autonomous blue- and red-team agents and cyber operations environments, and proposes criteria for judging whether autonomous network defence is ready for real deployment. It identifies gaps in explainability, continual learning under evolving threats, and realistic training environments.
Why it matters
It is a reference synthesis for what evidence would be needed before letting autonomous defenders act on live networks.
Key facts
As stated in the sources, with where to find them.
- The review presents criteria to evaluate the preparedness of autonomous agents for real-world networked environments and identifies gaps in explainability, continual learning and realistic training environments.Abstract
Findings that cite this record
No tracked finding cites this record yet.
Key questions this bears on
- Can prompt injection against AI agents be reliably defended?Not reliably. Bounding what untrusted input can trigger helps, but trust boundaries must survive delegation and tool execution.
Sources
Related records
Jun 27, 2025
Oct 27, 2026
Oct 13, 2026
Oct 12, 2026
Sep 30, 2026
Sep 28, 2026