Record summary
A quick snapshot of what this page covers.
Techniques8Attack methods connected to this risk.
Mitigations17Defenses 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
CategoryInference risks (Robustness)
SubcategoryExtraction attack
Suggested mitigations
Defenses that may help with related attacks.
Control Access to AI Models and Data at Rest
Business and Data UnderstandingData Preparation+2 more
AI Model Distribution Methods
Deployment
Passive AI Output Obfuscation
DeploymentML Model Evaluation
Model Hardening
Data PreparationML Model Engineering
Restrict Number of AI Model Queries
Business and Data UnderstandingDeployment+1 more
Use Ensemble Methods
ML Model Engineering
Input Restoration
Data PreparationML Model Evaluation+2 more
Adversarial Input Detection
Data PreparationML Model Engineering+3 more
Control Access to AI Models and Data in Production
DeploymentMonitoring and Maintenance
Encrypt Sensitive Information
Data PreparationML Model Engineering+1 more
Validate AI Model
ML Model EvaluationMonitoring and Maintenance
Restrict Library Loading
Deployment
Code Signing
Deployment
Verify AI Artifacts
Business and Data UnderstandingData Preparation+1 more
Vulnerability Scanning
ML Model EngineeringData Preparation
User Training
Business and Data UnderstandingData Preparation+4 more
AI Bill of Materials
Business and Data UnderstandingData Preparation+1 more
Source
Research source for this risk, when available.
Included resource
AI Risk Atlas
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.