Adversaries tamper with training, fine-tuning, or third-party data feeds behind the approved models, mislabeling data or embedding backdoor triggers and biases that corrupt downstream decisions without visible symptoms until a major failure.
AI/ML / Multi Agent Refarch / Threats / DEV
Foundation-model training and fine-tuning data poisoning
CCC.MARefArc.TH06
Related Capabilities
| ID | Title | Description |
|---|---|---|
| CCC.MARefArc.CP14 | Approved-model registry and lifecycle | Catalog of approved models with metadata, version information, configuration parameters, and usage constraints, ensuring agents access only models meeting organizational, regulatory, and security standards. |
Related Controls
| ID | Title | Description |
|---|---|---|
| CCC.MARefArc.CN01 | Data Filtering From External Knowledge Bases | Sanitize, filter, and classify data ingested by the Knowledge Layer from internal and external source bases before it is embedded into the vector store or used for retrieval-augmented generation, preventing inadvertent exposure or manipulation of sensitive organizational knowledge. |
| CCC.MARefArc.CN04 | Data Quality and Classification | Assess the quality of, and assign classification and sensitivity labels to, all data used for grounding, training, and fine-tuning, and enforce handling rules derived from those labels throughout the Knowledge and LLM layers. |
| CCC.MARefArc.CN08 | Role-Based Access Control for AI Data | Enforce least-privilege, role-based access control over all AI data stores, including source bases, the vector store, and model artifacts. |
External Mappings
| Framework | ID | Remarks |
|---|---|---|
| air-vec | AIR-SEC-009-01 | |
| air-vec | AIR-SEC-009-03 | |
| air-vec | AIR-SEC-009-04 |