APromptRiskDBThreat intelligence atlas
AI Risk

Data exfiltration

"Data Exfiltration goes beyond revealing private information, and involves illicitly obtaining the training data used to build a model that may be sensitive or proprietary. Model Extraction is the same attack, only directed at the model instead of the training data — it involves obtaining the architecture, parameters, or hyper-parameters of a proprietary model (Carlini et al., 2024)."

AI Risk2. Privacy & Security2.2 > AI system security vulnerabilities and attacks2 - Post-deployment

Record summary

A quick snapshot of what this page covers.

Techniques22Attack methods connected to this risk.
Mitigations21Defenses that may help with related attacks.
Domain2. Privacy & SecurityThe broad risk area this belongs to.

Risk profile

How this risk is described and categorized.

Domain2. Privacy & Security
Subdomain2.2 > AI system security vulnerabilities and attacks
Entity1 - Human
Intent1 - Intentional
Timing2 - Post-deployment
CategoryMisuse tactics to compromise GenAI systems (Data integrity)
SubcategoryData exfiltration

Suggested mitigations

Defenses that may help with related attacks.

Code Signing

Deployment
LifecycleDeploymentCategoryTechnical - Cyber

AI Telemetry Logging

DeploymentMonitoring and Maintenance
LifecycleDeployment + 1 moreCategoryTechnical - Cyber

Sanitize Training Data

Business and Data UnderstandingData Preparation+1 more
LifecycleBusiness and Data Understanding + 2 moreCategoryTechnical - ML

Validate AI Model

ML Model EvaluationMonitoring and Maintenance
LifecycleML Model Evaluation + 1 moreCategoryTechnical - ML

AI Bill of Materials

Business and Data UnderstandingData Preparation+1 more
LifecycleBusiness and Data Understanding + 2 moreCategoryPolicy

Verify AI Artifacts

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

Generative AI Guardrails

ML Model EngineeringML Model Evaluation+1 more
LifecycleML Model Engineering + 2 moreCategoryTechnical - ML

Source

Research source for this risk, when available.