Model Inversion Attacks for Prediction Systems: Without Knowledge of Non-Sensitive Attributes

By Seira Hidano, Takao Murakami, Shuichi Katsumata, S. Kiyomoto, Goichiro Hanaoka. 2017

77 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deduplicating Training Data Mitigates Privacy Risks in Language Models (2022, background): “Later model inversion attacks focus on fully recreating training samples given access to only a trained model (Hidano et al., 2017; Song & Raghunathan, 2020; Yang et al., 2019).”
A Survey of Privacy Attacks in Machine Learning (2020, methodology): “Name Data Type Learning Task Reference(s) Size (Samples) 538 Steak Survey [37] mixed features multi-class classification [14, 24, 38, 109] 332 AT&T Faces [4] images multi-class classification [24, 42, 119] 400 Bank Marketing [21] mixed features multi-class classification [116] 45,210 Bitcoin prices ”
Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment (2019, background): “org/conference/ usenixsecurity18/presentation/jia-jinyuan [44] S.”
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks (2019, background): “[11] proposed a algorithm that allows MI attacks to be carried out without the knowledge of nonsensitive features by poisoning training data properly.”
Neural Network Inversion in Adversarial Setting via Background Knowledge Alignment (2019, background): “Some work further improves sensitive attribute inference either by formalizing it [74] or without knowing the non-sensitive attributes [27].”