From 6c1a3b6fa8b8a48e8b6032b9c8a9f57dfbdb4b7a Mon Sep 17 00:00:00 2001
From: Zhanke Zhou <45969108+AndrewZhou924@users.noreply.github.com>
Date: Mon, 31 Oct 2022 21:35:07 +0800
Subject: [PATCH] Update README.md

---
 README.md | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index a835d68..3d7d1b3 100644
--- a/README.md
+++ b/README.md
@@ -3,9 +3,11 @@
 A curated list of resources for model inversion attack (MIA).
 
 ### What is the model inversion attack?
-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.
 
-(by Variational Model Inversion Attacks, Wang et al, 2021.)
+The goal of model inversion attacks is to recreate training data or sensitive attributes.
+(Chen et al, 2021.)
+
+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. (Wang et al, 2021.)
 
 ### Survey
 Arxiv 2021 - A Survey of Privacy Attacks in Machine Learning.