CCC.GenAI.TH09: Lack of Explainability
Threat ID:CCC.GenAI.TH09
Title:Lack of Explainability
Description:
The "black box" nature of GenAI models makes it difficult or impossible to understand the specific reasoning behind a given output. This opacity makes it challenging to diagnose failures, detect hidden biases, and meet regulatory requirements for decision transparency.
Related Capabilities
| ID | Title | Description |
|---|---|---|
| CCC.GenAI.F21 | Generate Content | Ability to generate a response given a foundation model, parameter values, and a prompt. |
External Mappings
| Reference ID | Entry ID | Strength | Remarks |
|---|---|---|---|
FINOS-AIGF | AIR-OP-017 | 0 | Lack of Explainability |
FINOS-AIGF | AIR-RC-022 | 0 | Regulatory Compliance and Oversight |
MITRE-ATLAS | AML.T0062.000 | 0 | LLM Trusted Output Components Manipulation: Citations |
Controls
| ID | Title | Objective | Control Family | Threat Mappings | Guideline Mappings | Assessment Requirements |
|---|---|---|---|---|---|---|
| CCC.GenAI.C05 | Citations and Source Traceability | Require the GenAI system to provide citations or direct links back to the source documents used to generate a response, in to enhance the transparency, trustworthiness, and verifiability of AI-generated content. | Data | 2 | 1 | 1 |