Evaluation design and benchmarks · MLD-1090
Security evaluation
Testing whether a system protects defined assets and trust boundaries against specified threats.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Assess prompt-injection defenses in a tool-using application.
Original caveat
A model-only evaluation can miss application-level vulnerabilities.
Context and aliases
Level: Intermediate. Stages: Evaluation · Research.
Tags: ML · DL · LLM · SLM · Safety.
Aliases: None recorded.