8 canonical risk pages
Privacy
Risks related to exposure, leakage, surveillance, and re-identification of data.
Data Brokerage
Commercialization of detailed psychological profiles and personal characteristics inferred by AI to third parties without the knowledge or consent of profiled individuals.
Mass Surveillance
Capability to perform automated analysis and continuous monitoring of entire populations using AI systems, including facial recognition and behavioral analysis at global scale.
Memorization
Exact storage of training data in model weights, allowing extraction of sensitive information via specific queries.
Privacy Leakage
Risk that the model reveals personally identifiable information (PII) memorized during training, exposing sensitive data of individuals without their consent.
Re-identification
Data linkage and correlation techniques on seemingly anonymized datasets that allow the identification of individuals, violating privacy guarantees.
Sensitive Inference
Deduction of sensitive personal information (sexual orientation, health status, political beliefs) from seemingly innocuous behavioral patterns.
Membership Inference
Attacks that determine if a specific record was part of the model's training set, violating privacy expectations.
Model Inversion
Techniques that reconstruct sensitive training data (e.g., faces, medical records) from model parameters or outputs.