Evaluating Explanation Methods for Deep Learning in Security
This repository contains code connected to the paper
Evaluating Explanation Methods for Deep Learning in Security, A.Warnecke, D.Arp, C. Wressnegger and K.Rieck, IEEE European Symposium on Security and Privacy (Euro S&P), 2020.
- NetworkTraining contains training scripts for the different networks/datasets used in the paper.
- Explanation contains scripts to calculate relevances for data and models with LEMNA and LIME.