Skip to content

Trustworthy Machine Learning

Welcome to the comprehensive resource hub for Trustworthy Machine Learning (TML). This site serves as a central repository for course materials, cutting-edge research, and community resources in the rapidly evolving field of trustworthy AI.

What is Trustworthy ML?

Trustworthy Machine Learning encompasses the principles and practices needed to build AI systems that are:

  • Fair and unbiased across different populations
  • Robust to adversarial attacks and distribution shifts
  • Transparent and interpretable in their decision-making
  • Privacy-preserving in how they handle sensitive data
  • Accountable for their predictions and recommendations

Course Overview

Our comprehensive course covers the fundamental concepts, state-of-the-art techniques, and practical implementations of trustworthy ML systems. Whether you're a student, researcher, or practitioner, you'll find valuable resources here.

Fall 2025 Course

The Trustworthy ML course is being offered in Fall 2025 at UCLA Extension. Check out the syllabus for detailed information about topics, schedule, and assignments, or enroll directly.

Quick Navigation

  • Fairness in AI: Bias detection, mitigation strategies, and fairness metrics
  • Adversarial Robustness: Defense mechanisms and robust training techniques
  • Explainable AI: Interpretability methods and transparency tools
  • Privacy-Preserving ML: Differential privacy, federated learning, and secure computation
  • AI Safety: Alignment, safety verification, and risk assessment

Stay Connected

Connect with the trustworthy ML community:


This resource is continuously updated with the latest research, tools, and community contributions.