An introduction to adversarial examples, with many details on machine learning and security. It was presented as a tutorial at IEEE WIFS 2019. More details can be found in the repository's README file.

A framework to index Github repositories to Neo4j, which enables large scale software repository mining using graph structures.

A Python experiment management framework that comes with algorithms and abstractions for training and testing models. The goal is to have only a configuration file for scheduling experiments, monitor and save experimental data.

A project to learn state representations from OpenAI environments. The representations can be used to formally verify the behaviour of reinforcement learning agents. It was developed by David, a student I supervised.

A curated data set of malware samples, and scripts to train machine learning algorithms. The data set can be used to benchmark algorithms for malware detection. It was developed by Coen, a student I supervised.