TRUSTWORTHY AI
TRUST4AI.XAI - Explainability of AI
A module to aid in explainability of supervised learning models.
TRUST4AI.Fairness - Fairness of AI
A module to study fairness (bias) metrics and bias mitigations in AI models.
TRUST4AI.Security - Security of AI
A solution to analyse adversarial machine learning (AML) threats and execute aversarial testing.