Differentially Private Genome Data Dissemination Through Top-Down Specialization
Offered By: USENIX via YouTube
Course Description
Overview
Explore a 24-minute conference talk from USENIX HealthTech '14 that presents a novel approach for disseminating genomic data while maintaining differential privacy. Learn about an algorithm that splits raw genome sequences into blocks, subdivides them using a top-down method, and adds noise to counts for privacy protection. Discover how this technique can potentially retain higher data utility compared to baseline methods for a given privacy budget. Understand its applicability to heterogeneous data, including combined medical and genomic records. Gain insights into possible future improvements, such as refining sequence splitting heuristics and introducing scoring functions in the data generalization process.
Syllabus
HealthTech '14 - Differentially Private Genome Data Dissemination Through Top-Down Specialization
Taught by
USENIX
Related Courses
Statistical Machine LearningCarnegie Mellon University via Independent Secure and Private AI
Facebook via Udacity Data Privacy and Anonymization in R
DataCamp Build and operate machine learning solutions with Azure Machine Learning
Microsoft via Microsoft Learn Data Privacy and Anonymization in Python
DataCamp