Topic

AI security testing

The use of machine-learning models, increasingly frontier models, to probe software for vulnerabilities and to assist the engineers who triage and fix them.

Current clusters

build1 publisher

Fleet runs its frontier-model security tests in temporary cloud accounts on synthetic data

Luke Heath's written answers to Lets Data Science put eight named controls around the model, among them scoped credentials, engineer approval and hand reproduction of every candidate finding. Heath has not disclosed results yet.

Publishers:letsdatascience.com

Reality

Evidence45
Adoption20
Hype gap−10
Incentives70
Confidence50