honeycluster

This GIT contains the code for the article "Towards NLP-based Processing of Honeypot Logs".

For the collected sessions, contact matteo.boffa@polito.it or idilio.drago@unito.it.

Each NLP technique (tfidf, Count Vectorizer and W2V) has its own notebook and saves the resulting files and images on the "./Results" folder.

Notice that, for each attempt, we're saving:

1. Dendorgram
2. Heatmap
3. Tuning trends for clustering