Explore a cutting-edge presentation on Locally Differentially Private Frequent Itemset Mining delivered at the 2018 IEEE Symposium on Security & Privacy. Delve into the concept of Local Differential Privacy (LDP) and its application in preserving user privacy when responding to sensitive questions. Examine the basic LDP frequent oracle (FO) protocol and its limitations when dealing with users having multiple values. Discover the newly introduced padding and sample based frequency oracles (PSFO) and their privacy amplification properties. Learn about SVIM, an innovative protocol for identifying frequent items in set-valued LDP settings, and its superior performance compared to existing methods. Investigate SVSM, a groundbreaking approach to finding frequent itemsets in the LDP context. Gain insights into the latest advancements in privacy-preserving data mining techniques and their potential applications in various fields.
Overview
Syllabus
Locally Differentially Private Frequent Itemset Mining
Taught by
IEEE Symposium on Security and Privacy
Tags
Related Courses
-
Locally Differentially Private Sparse Vector Aggregation
-
Locally Differentially Private Frequency Estimation Based on Convolution Framework
-
Learning Differentially Private Mechanisms
-
A Theory to Instruct Differentially-Private Learning via Clipping Bias Reduction
-
Differentially Private Histograms in the Shuffle Model from Fake Users
-
The Power of Differentially Oblivious Shuffle in Distributed Privacy Mechanisms
