ConceptPublic Ready
AI Product Supply Chain
An AI product is composed of models, prompts, policies, data, context, tools, orchestration, infrastructure, evaluations, and generated artifacts.
July 20, 2026Open
Start with the pressure: sales, launch, abuse, agents, data, or guardrails
Topic
Security of model artifacts, training and evaluation data, retrieval sources, embeddings, and model promotion workflows.
Research record
Research on model integrity, data provenance, promotion controls, poisoning, extraction, and artifact security.
Connected intelligence
An AI product is composed of models, prompts, policies, data, context, tools, orchestration, infrastructure, evaluations, and generated artifacts.
Organizations often treat the model as the AI product while under-modeling the data, context, prompts, tools, orchestration, infrastructure, and generated artifacts around it.
Differential privacy and privacy-preserving ML remain active arXiv research terms (112 and 32 papers in the current pull), but privacy still appears in hiring language mainly as a GDPR/compliance checkbox rather than a named engineering capability.
What companies really mean by AI Security Engineer and why the operating model is lagging the technology.