Explore the concept of property inference from poisoning in this 19-minute IEEE conference talk. Delve into the research presented by Saeed Mahloujifar from Princeton University, along with Esha Ghosh and Melissa Chase from Microsoft Research. Gain insights into the potential security implications and challenges associated with property inference attacks in machine learning models.
Overview
Syllabus
Property Inference from Poisoning
Taught by
IEEE Symposium on Security and Privacy
Tags
Related Courses
-
SNAP - Efficient Extraction of Private Properties with Poisoning
-
Manipulating Machine Learning - Poisoning Attacks and Countermeasures for Regression Learning
-
Membership Inference Attacks from First Principles
-
SoK - Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning
-
RAB - Provable Robustness Against Backdoor Attacks
-
Comprehensive Privacy Analysis of Deep Learning
