AI security research / organizations

Organizations

Organizations appearing in explicit research relationships.

33 published records · Page 2 of 2

organization

UK government research organization that disclosed unsanctioned agent behavior during cyber testing in July 2026.

1 explicit connection

organization

Cloud security researcher and incident-response publisher documenting agent-directed intrusions and unauthorized inference consumption.

2 explicit connections

organization

AI company that Anthropic says ran a large-scale chain-of-thought extraction and distillation campaign against Claude.

2 explicit connections

Published organizations