Skip to content

AI Runtime Security Detection Categories and Severity Levels

AI Runtime Security defines attacks by technique, providing an estimated severity level and definitions.

Detection Category Estimated Severity Definition
Data LeakageMediumThe unintentional or unauthorized exposure of sensitive data — such as Personally Identifiable Information (PII) — in model inputs or outputs.
Denial of ServiceMediumAn attempt to disrupt or degrade a large language model's performance and availability by overwhelming its resources or exploiting vulnerabilities.
Guardrail ActivationLowThe triggering of built-in safety mechanisms designed to prevent a large language model from generating harmful, misleading, or inappropriate content.
Language RestrictionMediumThe restriction of model inputs based on detected language, blocking or flagging content that falls outside permitted languages.
Modality RestrictionLowThe restriction of model inputs and outputs based on their modality type, including but not limited to code detection.
Prompt InjectionHighThe manipulation of an input prompt to cause a large language model to generate undesired, misleading, or harmful responses.