A general framework for constructing partial dependence (i.e., marginal effect) plots from various types machine learning models in R.

Simplicial Homology Global Optimization

This repository was created as an implementation approach for a project on "Watermarking Deep Neural Networks".

Tiny Tutorial on https://arxiv.org/abs/1703.04730

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

Black-box Few-shot Knowledge Distillation

Generative Adversarial Network (GAN) that can produce tabular samples given datasets, and build a general generative model that receives a black-box as a discriminator and can still generate samples from the tabular data.

Getting explanations for predictions made by black box models.

Using LIME and SHAP for model interpretability of Machine Learning Black-box models.

A Global Model-Agnostic Rule-Based XAI Method based on Parameterised Event Primitives for Time Series Classifiers

Interpreting Categorical Data Classifiers using Explanation-based Locality