Privacy-Preserving Machine Learning

Explore privacy-preserving machine learning techniques in this 31-minute conference talk by Patricia Thaine, CEO of Private AI and PhD Candidate at the University of Toronto. Gain strategic insights into addressing privacy challenges in machine learning pipelines through practical examples. Learn about various privacy tools including federated learning, homomorphic encryption, differential privacy, anonymization/pseudonymization, secure multiparty computation, and trusted execution environments. Understand how to evaluate and implement these tools based on risk assessment, implementation complexity, and available computational resources. Discover effective approaches to create privacy-preserving machine learning solutions for organizations facing diverse privacy goals.