Record summary
A quick snapshot of what this page covers.
Techniques3Attack methods connected to this risk.
Mitigations8Defenses 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
Timing3 - Other
CategoryModel Development
SubcategoryTraining-related (Robustness certificates can be exploited to attack the models)
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
Model Hardening
Data PreparationML Model Engineering
Use Ensemble Methods
ML Model Engineering
Use Multi-Modal Sensors
Business and Data UnderstandingData Preparation+1 more
Input Restoration
Data PreparationML Model Evaluation+2 more
Adversarial Input Detection
Data PreparationML Model Engineering+3 more
Deepfake Detection
DeploymentMonitoring and Maintenance+2 more
Source
Research source for this risk, when available.
Included resource
Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.