Record summary
A quick snapshot of what this page covers.
Techniques6Attack methods connected to this risk.
Mitigations13Defenses 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
Entity1 - Human
Intent1 - Intentional
Timing2 - Post-deployment
CategoryInstruction Attacks
SubcategoryPrompt Leaking
Suggested mitigations
Defenses that may help with related attacks.
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
Verify AI Artifacts
Business and Data UnderstandingData Preparation+1 more
AI Bill of Materials
Business and Data UnderstandingData Preparation+1 more
AI Telemetry Logging
DeploymentMonitoring and Maintenance
Privileged AI Agent Permissions Configuration
Deployment
Single-User AI Agent Permissions Configuration
Deployment
AI Agent Tools Permissions Configuration
Deployment
Human In-the-Loop for AI Agent Actions
Deployment
Restrict AI Agent Tool Invocation on Untrusted Data
Deployment
Segmentation of AI Agent Components
DeploymentBusiness and Data Understanding
Input and Output Validation for AI Agent Components
Business and Data UnderstandingData Preparation+1 more
Source
Research source for this risk, when available.
Included resource
Safety Assessment of Chinese Large Language Models
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.