[arXiv:2411.10023] "Model Inversion Attacks: A Survey of Approaches and Countermeasures"

Membership Inference, Attribute Inference and Model Inversion attacks implemented using PyTorch.

Official implementation of "Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective"

Unofficial pytorch implementation of paper: Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures

[ICML 2023] "On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation"

[ICML 2023] "On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation"

📄 [Talk] OFFZONE 2022 / ODS Data Halloween 2022: Black-box attacks on ML models + with use of open-source tools

Official code for paper: Z. Zhang, X. Wang, J. Huang and S. Zhang, "Analysis and Utilization of Hidden Information in Model Inversion Attacks," in IEEE Transactions on Information Forensics and Security, doi: 10.1109/TIFS.2023.3295942

My attempt to recreate the attack described in "Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures" by Fredrikson et al. in 2015 using Tensorflow 2.9.1

Universität des Saarlandes - Privacy Enhancing Technologies 2021 - Semester Project

torchplus is a utilities library that extends pytorch and torchvision

Implementation of "An Approximate Memory based Defense against Model Inversion Attacks to Neural Networks" and "MIDAS: Model Inversion Defenses Using an Approximate Memory System"

Official code for paper: Z. Zhang and J. Huang, “Aligning the domains in cross domain model inversion attack,” Neural Networks, vol. 178, p. 106490, Oct. 2024, doi: 10.1016/j.neunet.2024.106490.

Collection of code of the model inversion attacks proposed by me.

Official code for paper: Z. Zhang, J. Huang, and C. Ding, “Flexible Model Inversion Attack with soft biometric attribute reconstruction against face classifiers,” Journal of Systems Architecture, p. 103739, Feb. 2026, doi: 10.1016/j.sysarc.2026.103739.

Linear regression and ML attack experiments.

Official code for paper: Z. Zhang and J. Huang, “Exploiting the connections between images and deep feature vectors in model inversion attacks,” Neurocomputing, p. 131457, Sept. 2025, doi: 10.1016/j.neucom.2025.131457.