A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning. arXiv:2307.09218.
-
Updated
Sep 19, 2024
A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning. arXiv:2307.09218.
A comprehensive toolbox for model inversion attacks and defenses, which is easy to get started.
Code for ML Doctor
[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 curated list of resources for model inversion attack (MIA).
Security and Privacy Risk Simulator for Machine Learning (arXiv:2312.17667)
Research into model inversion on SplitNN
Bilateral Dependency Optimization: Defending Against Model-inversion Attacks
[CVPR-2023] Re-thinking Model Inversion Attacks Against Deep Neural Networks
[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
Unofficial pytorch implementation of paper: Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
📄 [Talk] OFFZONE 2022 / ODS Data Halloween 2022: Black-box attacks on ML models + with use of open-source tools
[CVPR-2023] Re-thinking Model Inversion Attacks Against Deep Neural Networks
Implementation of the Model Inversion Attack introduced with Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures (Fredrikson Et al.)
Implementation of the model inversion attack on the Gated-Recurrent-Unit neural network
Implementation of "An Approximate Memory based Defense against Model Inversion Attacks to Neural Networks" and "MIDAS: Model Inversion Defenses Using an Approximate Memory System"
reveal the vulnerabilities of SplitNN
Add a description, image, and links to the model-inversion-attacks topic page so that developers can more easily learn about it.
To associate your repository with the model-inversion-attacks topic, visit your repo's landing page and select "manage topics."