APromptRiskDBThreat intelligence atlas
AI Security Technique

Discover AI Model Ontology - AI Security Technique

Adversaries may discover the ontology of an AI model's output space, for example, the types of objects a model can detect. The adversary may discovery the ontology by repeated queries to the model, forcing it to enumerate its output space. Or the ontology may be discovered in a configuration file or in documentation about the model. The model ontology helps the adversary understand how the model is being used by t...

AI Security TechniquedemonstratedDiscovery

Record summary

A quick snapshot of what this page covers.

Tactics1Attacker goals connected to this method.
Mitigations2Defenses that may help against this attack.
AI risks0Research-backed risks connected to this topic.

Attack context

How this AI attack works in practice.

Adversaries may discover the ontology of an AI model's output space, for example, the types of objects a model can detect. The adversary may discovery the ontology by repeated queries to the model, forcing it to enumerate its output space. Or the ontology may be discovered in a configuration file or in documentation about the model.

The model ontology helps the adversary understand how the model is being used by the victim. It is useful to the adversary in creating targeted attacks.

ATLAS ID
AML.T0013
Priority score
36
Maturity: demonstrated
Discovery

Mitigations

Defenses that may help against this attack.

AML.M0002 - Passive AI Output Obfuscation

DeploymentML Model Evaluation
LifecycleDeployment + 1 moreCategoryTechnical - ML

Suggested approaches:

  • Restrict the number of results shown
  • Limit specificity of output class ontology
  • Use randomized smoothing techniques
  • Reduce the precision of numerical outputs

AML.M0004 - Restrict Number of AI Model Queries

Business and Data UnderstandingDeployment+1 more
LifecycleBusiness and Data Understanding + 2 moreCategoryTechnical - Cyber

Limit the amount of information an attacker can learn about a model's ontology through API queries.

Case studies

Examples from public reports and exercises.

Face Identification System Evasion via Physical Countermeasures

exercise
Date2020-01-01

MITRE's AI Red Team demonstrated a physical-domain evasion attack on a commercial face identification service with the intention of inducing a targeted misclassification. This operation had a combination of traditional MITRE ATT&CK techniques such as finding valid accounts and executing code via an API - all interleaved with adversarial ML specific attacks.

Source

Where this page information comes from.