Record summary
A quick snapshot of what this page covers.
Risk profile
How this risk is described and categorized.
"Technical AI hazards are the root causes of technical deficiencies in the AI system. An example of such an AI hazard is overfitting, which describes a model’s excessive adaptation to the training dataset. Quantitative methods to assess (metrics) and treat (mitigation means) exist for technical AI hazards, which might be performed automatically. In case of overfitting, metrics are based on the comparison of performance between the training and validation datasets, and mitigation means may include regularization techniques, among others."
Suggested mitigations
Defenses that may help with related attacks.
Limit Model Artifact Release
Verify AI Artifacts
AI Bill of Materials
Maintain AI Dataset Provenance
Control Access to AI Models and Data at Rest
Validate AI Model
Code Signing
Source
Research source for this risk, when available.
Included resource
AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.