Record summary
A quick snapshot of what this page covers.
Techniques5Attack methods connected to this risk.
Mitigations12Defenses 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
Subdomain2.1 > Compromise of privacy by leaking or correctly inferring sensitive information
Entity2 - AI
Intent2 - Unintentional
Timing2 - Post-deployment
CategoryRisk area 2: Information Hazards
SubcategoryCompromising privacy by leaking sensitive information
Suggested mitigations
Defenses that may help with related attacks.
Passive AI Output Obfuscation
DeploymentML Model Evaluation
Restrict Number of AI Model Queries
Business and Data UnderstandingDeployment+1 more
AI Telemetry Logging
DeploymentMonitoring and Maintenance
Validate AI Model
ML Model EvaluationMonitoring and Maintenance
Generative AI Guardrails
ML Model EngineeringML Model Evaluation+1 more
Generative AI Guidelines
ML Model EngineeringML Model Evaluation+1 more
Generative AI Model Alignment
ML Model EngineeringML Model Evaluation+1 more
Control Access to AI Models and Data at Rest
Business and Data UnderstandingData Preparation+2 more
Sanitize Training Data
Business and Data UnderstandingData Preparation+1 more
Verify AI Artifacts
Business and Data UnderstandingData Preparation+1 more
Maintain AI Dataset Provenance
Data PreparationBusiness and Data Understanding
AI Bill of Materials
Business and Data UnderstandingData Preparation+1 more
Source
Research source for this risk, when available.
Included resource
Taxonomy of Risks posed by Language Models
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.