The COMPEL Glossary Graph visualizes relationships between framework terminology, showing how concepts interconnect across domains, stages, and pillars. Term nodes cluster by pillar affiliation while cross-references reveal semantic dependencies — for example, how risk appetite connects to control effectiveness, model governance, and assurance requirements. This network representation helps practitioners navigate the framework vocabulary and understand that COMPEL terminology forms a coherent conceptual system rather than isolated definitions.
COMPEL Glossary / red-team-for-llms
Red-team (for LLMs)
A structured adversarial exercise against an LLM feature using human, automated, or hybrid techniques drawn from MITRE ATLAS or OWASP LLM Top 10 to discover failure modes before attackers do.
What this means in practice
Extends classical red-teaming with LLM-specific techniques such as jailbreak suite probes, indirect prompt injection payloads, and tool-use attack chains.
Synonyms
LLM red-teaming , adversarial LLM testing , generative red team
See also
- Evaluation harness — The infrastructure that runs capability, regression, safety, and human-review evaluations on an LLM feature on a defined cadence.
- Jailbreak — A user-crafted prompt pattern that bypasses a model's safety training to elicit restricted behavior.
- Guardrail — A control placed between the user or environment and an LLM that blocks, rewrites, or classifies content at one of four architectural layers: input filter, policy filter, output filter, or tool-call validator.