SecGen is a joint team between Inria and CISPA, working together on the subject of network traffic generation and network anomaly detection. Intrusion detection is an essential mechanism in information systems security. Machine learning has been successfully applied to this problem. These techniques rely on training data used to train a detection model. This training data generally comes from datasets that are often more or less automatically generated. Worse, the number of datasets remains small enough that the diversity of the dataset is questionable, and its aging is problematic. A solution to these problems is synthetic data generation: it would be free of experimental inaccuracies, could be easily updated, and alleviate the class imbalance by generating more data on rare classes. We plan to generate benign data only, as attacks are easier to generate with dedicated tools.

Participants from Inria:

  • Dr Pierre-François Gimenez (coordinator), research scientist at Inria with a PhD in machine learning. Intrusion detection expert.
  • Prof Ludovic Mé, advanced research position at Inria. Intrusion detection expert.
  • Dr Yufei Han, advanced research position at Inria. Expert in AI for security and security of AI.
  • Dr Frédéric Majorczyk, engineer at DGA-MI and external member of Inria. Network security expert.
  • Hélène Orsini, PhD student at Inria. Works on auto-ML intrusion detection on traffic data.
  • Adrien Schoen, PhD student at Inria. Works on network data generation.
  • Matthieu Mouzaoui, PhD student at Inria. Works on adversarial attacks on intrusion detection systems.

Participants from CISPA:

  • Prof Mario Fritz (coordinator), professor at CISPA. Works on security of machine learning, with a focus on privacy and robustness.
  • Prof Jilles Vreeken, professor at CISPA. Works on data mining, e.g., for causal or temporal dependency identification.
  • Dr Lénaïg Cornanguer, post-doctoral researcher at CISPA. Works on machine learning and data mining.
  • Sarath Sivaprasad, PhD student at CISPA. Works on deep learning models.
  • Joscha Cueppers, PhD student at CISPA. Works on data mining.