Projects

Social Media Intelligence

The goal is firstly to propose a method to collect social media data regarding a specific subject (e.g. elections narratives, brand image...) in a semi-automatic way. Secondly the focus is on:

  1. near-real time analysis and visualization
  2. pattern recognition in the longer term based on a network approach
Discover
Cyber Range

Our cyber range uses scenario descriptors to automatically:

  1. download required images from Vagrant
  2. deploy and configure the virtual machines
  3. configure required virtual networks
  4. install additional software
  5. configure the web interface such that trainees and techers can easily access their machines
Discover Connect
ECHO

European network of Cybersecurity centers and competence Hub for innovations and Operations (ECHO).

ECHO is a 48-month project to develop a network of cyber research and competence centres throughout Europe, with a central support hub. The main area of focus are:

  • Multi-sector assessment framework;
  • Early warning system;
  • Federated Cyber Range;
  • Cyberskills framework;
  • Cybersecurity certification scheme.
Read more
Java WOWA Training

The WOWA operator (Torra) is a powerfull aggregation operator that allows to aggregate multiple input values into a single score. This is particularly interesting for detection and ranking systems that rely on multiple heuristics. The system can use WOWA to produce a single meaningful score.

In this project we use a genetic algorithm to compute the best parameters for the WOWA operator. For the training, the algorithm uses a dataset of input vectors together with the expected aggregated score of each vector.

The Java library is available on Maven.

Read more
PHP WOWA Training

A PHP implementation of the WOWA training algorithm. The library is available on Composer.

Read more
Multi Agent Ranking Framework

The multi-agent ranking framework (MARK) aims to provide all the building blocks that are required to build large scale detection and ranking systems.

Read more
Phishing awareness

Our phish-me tool allows to easily organize phishing awareness campaigns.

Discover
Graph based APT detection

The focus of APT-GRAPH is the detection of Advanced Persistent Threat (APT). More specifically, the aim is to study proxy log files and to detect a domain used as Command and Control (C2) by an APT. The implemented algorithm models the traffic by means of a graph and tries to detect infections by looking for anomaly within this graph.

Read more
Detection of webshells

The webshell detector uses multiple techniques, including fuzzy hashing and anomaly detection, to detect webshells.

It can be integrated as a composer library to your project, or you can run it from the command line.

Read more
Detection of rogue IoT devices

The goal of this project is to monitor IoT traffic of a SOHO (Small Office, Home Office) network. By sniffing and analyzing this traffic, the smart router can send alerts when an IoT has an unusual network traffic.

Read more
Spark k-nn graphs

Spark algorithms for building and processing k-nn graphs.

Read more
Java String Similarity

Java implementation of various string similarity and distance algorithms: Levenshtein, Jaro-winkler, n-Gram, Q-Gram, Jaccard index, Longest Common Subsequence edit distance, cosine similarity...

Read more
MongoDB Proxy

A proxy for MongoDB written in Java. Using this proxy allows to easily trigger additional actions when data is inserted in the database for example.

Read more
Data Diode

A data diode that allows to route multiple UDP streams from and to different servers, using a simple web interface.

Read more