STRIDE
A threat classification mnemonic: Spoofing, Tampering, Repudiation, Information disclosure, Denial of service, Elevation of privilege.
Updated
STRIDE gives a structured pass over each element of a data-flow diagram, so threat identification is systematic rather than dependent on who happens to be in the room.
It applies unchanged to AI systems; what changes is which mitigations are effective, because untrusted input can act as instructions. The six categories still map onto agent trust boundaries, but STRIDE has no native category for prompt injection, so current practice pairs it with MITRE ATLAS or an added AI-specific category.
Related
Threat modeling
A practical STRIDE-based threat modeling method for cloud, application and AI systems, built to be run by engineering teams.
STRIDE for AI systems
Applying STRIDE to LLM and agentic applications: what each category means when untrusted text can act as instructions, where STRIDE stops covering multi-agent failure modes, and the controls per element.
Threat modeling
Facilitated STRIDE threat modeling on your real architecture, plus the templates and coaching to keep teams doing it without me.
Three layers, three risk profiles
A security review that skips naming its layer — model, service, or agent — ends up testing the wrong attack surface.
Agentic threat models
Why the shift from generative query-response to an autonomous agentic loop changes the threat model of an AI system from bad output to unintended action.
From Threat Modeling to a General Principle
Thoughts on threat modeling