threats

GumGum Threat (GGThreat) categories are part of GumGum's custom brand safety taxonomy. GumGum classifies content into nine GGThreat categories. 

Text analyses supports all nine categories; image analyses is relevant to seven of the nine categories. Verity evaluates the text and image threat scores and assigns the worst threat score to the category.

ValueDescription
GGT1Violence and gore.
GGT2Criminal.
GGT3Drugs and alcohol.
GGT4Sexually charged.
GGT5Profanity and vulgarity.
GGT6Hate speech, harassment, and cyberbullying.
GGT7Disasters.
GGT8Malware and phishing.
GGT9Medical.


The level of confidence in the Threat category designation is indicated as follows
AttributeConfidence Level
confidenceVERY_LOW
LOW
MODERATE
HIGH
VERY_HIGH


The level of risk in the Threat category designation is indicated as follows
AttributeConfidence Level
riskLOW
MEDIUM
HIGH


Syntax
"threats": [
 {
  "id": "<Threat Category ID>",
  "category": "<Threat Category Name>",
  "confidence": "<Level>",
  "risk": "<Level>"
 }
]
Example
    "threats": [
      {
        "id": "GGT7",
        "category": "Disasters",
        "confidence": "MODERATE",
        "risk": "MEDIUM"
      }

Data Type

Array of objects
RequiredIncluded only if threats are detected. If no threats are detected, the threats array is empty.
More Information/wiki/spaces/VDOC/pages/930545669

The contents of these documents and any attachments contain GumGum, Inc. confidential information and are legally protected from disclosure.