diff --git a/README.md b/README.md
index 2ff5434..5a9af16 100644
--- a/README.md
+++ b/README.md
@@ -131,6 +131,7 @@ Reconstruction attacks cover also attacks known as *model inversion* and *attrib
 - [**MIDAS: Model Inversion Defenses Using an Approximate Memory System**](https://ieeexplore.ieee.org/abstract/document/9358254) (Xu et al., 2021)
 - [**KART: Privacy Leakage Framework of Language Models Pre-trained with Clinical Records**](https://arxiv.org/abs/2101.00036) (Nakamura et al., 2020)
 - [**Derivation of Constraints from Machine Learning Models and Applications to Security and Privacy**](https://hal.archives-ouvertes.fr/hal-03091740/) (Falaschi et al., 2021)
+- [**On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Models**](https://arxiv.org/abs/2103.07101) (Zhao et al., 2021)
 
 
 ## Property inference