Web: http://arxiv.org/abs/2201.10787

Jan. 27, 2022, 2:10 a.m. | Kuan-Chieh Wang, Yan Fu, Ke Li, Ashish Khisti, Richard Zemel, Alireza Makhzani

cs.LG updates on arXiv.org arxiv.org

Given the ubiquity of deep neural networks, it is important that these models
do not reveal information about sensitive data that they have been trained on.
In model inversion attacks, a malicious user attempts to recover the private
dataset used to train a supervised neural network. A successful model inversion
attack should generate realistic and diverse samples that accurately describe
each of the classes in the private dataset. In this work, we provide a
probabilistic interpretation of model inversion attacks, …

arxiv attacks model

More from arxiv.org / cs.LG updates on arXiv.org

Director, Data Engineering and Architecture

@ Chainalysis | California | New York | Washington DC | Remote - USA

Deep Learning Researcher

@ Topaz Labs | Dallas, TX

Sr Data Engineer (Contractor)

@ SADA | US - West

Senior Cloud Database Administrator

@ Findhelp | Remote

Senior Data Analyst

@ System1 | Remote

Speech Machine Learning Research Engineer

@ Samsung Research America | Mountain View, CA