Class: DatadogAPIClient::V2::AIGuardConfidenceThreshold

Inherits:
Object
  • Object
show all
Includes:
BaseGenericModel
Defined in:
lib/datadog_api_client/v2/models/ai_guard_confidence_threshold.rb

Overview

Request-level confidence threshold override. flagging_global is the global threshold applied to every threat category. Any other property is a per-category override keyed by an AI Guard threat tag; per-category values take precedence over flagging_global, and categories without an entry fall back to it. When this object omits flagging_global, the fallback is 0.5. Recognized category keys include policy-evasion, indirect-prompt-injection, system-and-capability-discovery, credential-access, sensitive-data-collection, privilege-escalation, malicious-execution, private-network-target, destructive-or-resource-abuse, tool-abuse, poisoning-or-persistence, and data-exfiltration. Unknown category keys are ignored.

Instance Attribute Summary collapse

Method Summary

Methods included from BaseGenericModel

included

Instance Attribute Details

#additional_properties ⇒ Object

Returns the value of attribute additional_properties.



36
37
38
 
# File 'lib/datadog_api_client/v2/models/ai_guard_confidence_threshold.rb', line 36

def additional_properties
  @additional_properties
end

#flagging_global ⇒ Object

The global confidence threshold applied to categories without a specific override.



34
35
36
 
# File 'lib/datadog_api_client/v2/models/ai_guard_confidence_threshold.rb', line 34

def flagging_global
  @flagging_global
end