Label-Only Model Inversion Attacks via Boundary Repulsion

1 code implementation • CVPR 2022 • Mostafa Kahla, Si Chen, Hoang Anh Just, Ruoxi Jia

In this paper, we introduce an algorithm, Boundary-Repelling Model Inversion (BREP-MI), to invert private training data using only the target model's predicted labels.

Face Recognition

Knowledge-Enriched Distributional Model Inversion Attacks

2 code implementations • ICCV 2021 • Si Chen, Mostafa Kahla, Ruoxi Jia, Guo-Jun Qi

We present a novel inversion-specific GAN that can better distill knowledge useful for performing attacks on private models from public data.