Explore a 16-minute IEEE conference talk on SNAP (Efficient Extraction of Private Properties with Poisoning), presented by researchers from Northeastern University, Google Research, and ETH Zurich. Delve into the innovative technique for extracting private properties through poisoning attacks, understanding its efficiency and implications for data privacy and security. Gain insights into the collaborative work of experts in the field as they discuss the methodology, challenges, and potential impact of SNAP on privacy-preserving machine learning and data protection strategies.
SNAP - Efficient Extraction of Private Properties with Poisoning
Overview
Syllabus
SNAP: Efficient Extraction of Private Properties with Poisoning
Taught by
IEEE Symposium on Security and Privacy
Tags
Related Courses
-
Locally Differentially Private Frequent Itemset Mining
-
Manipulating Machine Learning - Poisoning Attacks and Countermeasures for Regression Learning
-
Property Inference from Poisoning
-
D-DAE - Defense-Penetrating Model Extraction Attacks
-
Learning Differentially Private Mechanisms
-
Fine-Grained Poisoning Attack to Local Differential Privacy Protocols for Mean and Variance Estimation
