This repository contains the code for the two following papers:
- The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations, Laugel T., Lesot M.J., Marsala C., Renard X., Detyniecki M. - IJCAI 2019
- Unjustified Classification Regions and Counterfactual Explanations in Machine Learning, Laugel T., Lesot M.J., Marsala C., Renard X., Detyniecki M. - ECML-PKDD 2019
The clode includes an implementation of the LRA (Local Risk Assessment) and the VE (Vulnerability Evaluation) algorithms, described in the aforementioned articles.
Current code has not been cleaned and still lacks some dependencies. Current code will be split in two for each article.