Security and Privacy Risk Simulator for Machine Learning (arXiv:2312.17667)

A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning. TPAMI, 2024.

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

A comprehensive toolbox for model inversion attacks and defenses, which is easy to get started.

Code for ML Doctor

Implementation of the Model Inversion Attack introduced with Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures (Fredrikson Et al.)

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

[ICML 2022 / ICLR 2024] Source code for our papers "Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks" and "Be Careful What You Smooth For".

[CVPR-2023] Re-thinking Model Inversion Attacks Against Deep Neural Networks

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

reveal the vulnerabilities of SplitNN

[KDD 2022] "Bilateral Dependency Optimization: Defending Against Model-inversion Attacks"

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

Research into model inversion on SplitNN

📄 [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

[NeurIPS 2024] "Pseudo-Private Data Guided Model Inversion Attacks"

[CVPR-2023] Re-thinking Model Inversion Attacks Against Deep Neural Networks

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"