SPLSilicon Psyche LabsUnderstand & tune your AI

← News

News & insights

AI security & psychology

Attacks that work on people and on models alike: pressure, authority, urgency, and how to read them.

CPF3: the psychological vulnerability frameworkThe pre-cognitive weaknesses attackers exploit, mapped to security controls.cpf3.org ↗How CPF3 maps onto model behaviourThe same pressure patterns, read on AI models.

The first articles of this section are in review.