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

a gradient-based optimisation routine for highly parameterised non-linear dynamical models

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

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

Research into model inversion on SplitNN

Code for "Variational Model Inversion Attacks" Wang et al., NeurIPS2021

reveal the vulnerabilities of SplitNN

[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".

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

Privacy Testing for Deep Learning