The course teaches learners how to manage data securely while protecting users' personal information and implementing privacy-preserving techniques in machine learning models. The topics covered include anonymization and pseudonymization techniques such as k-anonymity and differential privacy. The course aims to equip participants with the skills to handle data securely and ensure the privacy of individuals. The teaching method involves discussing real-world scenarios and demonstrating various privacy-preserving methods. This course is intended for individuals interested in data privacy, security, and machine learning.
Privacy-Preserving Methods - Building Secure Projects
Overview
Syllabus
Intro
Privacy-preserving methods: Building secure projects
You want to collect and release data that contains answers to sensitive questions
You want to collect and release data that eontains answers te sensitive questions
You want to make generalizations over a population
In the context of a database Given we perform some query on the database we remove a person from the database and the query does not change then that person's privacy is fully protected
You want to use prediction models with user's data
You want to update your model with user's data
Taught by
PyCon US
Related Courses
-
Data Privacy and Anonymization in Python
-
Teaching Impacts of Technology: Data Collection, Use, and Privacy
-
Differential Privacy at Scale - Uber and Berkeley Collaboration - USENIX Enigma - 2018
-
Practical Privacy-Preserving Machine Learning in Python
-
How Anonymous Is My Anonymized Data?
-
Preserving Data Privacy in Federated Learning - Xiaokui Xiao
4.0
