Record summary
A quick snapshot of what this page covers.
Techniques11Attack methods connected to this risk.
Mitigations22Defenses that may help with related attacks.
Domain5. Human-Computer InteractionThe broad risk area this belongs to.
Risk profile
How this risk is described and categorized.
Domain5. Human-Computer Interaction
Subdomain5.1 > Overreliance and unsafe use
Entity3 - Other
Intent2 - Unintentional
Timing2 - Post-deployment
CategoryHuman-Computer Interaction Harms
SubcategoryCreating avenues for exploiting user trust, nudging or manipulation
Suggested mitigations
Defenses that may help with related attacks.
User Training
Business and Data UnderstandingData Preparation+4 more
Deepfake Detection
DeploymentMonitoring and Maintenance+2 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
Segmentation of AI Agent Components
DeploymentBusiness and Data Understanding
Passive AI Output Obfuscation
DeploymentML Model Evaluation
Restrict Number of AI Model Queries
Business and Data UnderstandingDeployment+1 more
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
Human In-the-Loop for AI Agent Actions
Deployment
Restrict AI Agent Tool Invocation on Untrusted Data
Deployment
Input and Output Validation for AI Agent Components
Business and Data UnderstandingData Preparation+1 more
Restrict Library Loading
Deployment
Verify AI Artifacts
Business and Data UnderstandingData Preparation+1 more
Vulnerability Scanning
ML Model EngineeringData Preparation
AI Bill of Materials
Business and Data UnderstandingData Preparation+1 more
Control Access to AI Models and Data in Production
DeploymentMonitoring and Maintenance
Encrypt Sensitive Information
Data PreparationML Model Engineering+1 more
AI Model Distribution Methods
Deployment
Source
Research source for this risk, when available.
Included resource
Ethical and social risks of harm from language models
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.
