Record summary
A quick snapshot of what this page covers.
Techniques16Attack methods connected to this risk.
Mitigations15Defenses 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
Entity2 - AI
Intent2 - Unintentional
Timing1 - Pre-deployment
CategorySoftware Security Issues
SubcategorySoftware Supply Chains
Suggested mitigations
Defenses that may help with related attacks.
Use Ensemble Methods
ML Model Engineering
Code Signing
Deployment
Verify AI Artifacts
Business and Data UnderstandingData Preparation+1 more
Generative AI Guardrails
ML Model EngineeringML Model Evaluation+1 more
AI Bill of Materials
Business and Data UnderstandingData Preparation+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
Maintain AI Dataset Provenance
Data PreparationBusiness and Data Understanding
Restrict Library Loading
Deployment
Vulnerability Scanning
ML Model EngineeringData Preparation
User Training
Business and Data UnderstandingData Preparation+4 more
Limit Model Artifact Release
Business and Data UnderstandingDeployment
Validate AI Model
ML Model EvaluationMonitoring and Maintenance
Generative AI Guidelines
ML Model EngineeringML Model Evaluation+1 more
Generative AI Model Alignment
ML Model EngineeringML Model Evaluation+1 more
Source
Research source for this risk, when available.
Included resource
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.