Post-doctoral Research Visit F/m Data Augmentation - Strasbourg, France - Inria

Inria

Entreprise vérifiée

Strasbourg, France

il y a 1 semaine

Posté par:

Sophie Dupont

beBee Recruiter

Description

Le descriptif de l'offre ci-dessous est en Anglais_

Type de contrat :

CDD

Niveau de diplôme exigé :
Thèse ou équivalent

Fonction :
Post-Doctorant

Contexte et atouts du poste:

The offered position is proposed by the RESIST team of the Inria Nancy Grand Est research lab, the French national public institute dedicated to research in digital Science and technology.

The team is one of the European research group in network management and is particularly focused on empowering scalability and security of networked systems through a strong coupling between monitoring, analytics and network orchestration.

Mission confiée:

Techniques used by both attackers and defenders evolve to complex mechanisms.

For example, this leads to the massive use of encryption to avoid data leaks but simultaneously attackers benefit from encryption to hide their own activities.

Multiple steps attacks also requires to analyze numerous sources of data. As a result, intrusion detection methods relying on artificial intelligence have been investigated both in research and in industry.

While these techniques hold promise for detecting and mitigating cyber threats, their effectiveness is highly dependent on the quality of the learning phase.

Despite significant progress, experiments and reports suggest that these tools still struggle to generalize effectively to new and previously unseen data, particularly when faced with minor variations compared to training data.

Actually, the learning suffers from the lack of enough labeled data to represent the different and possibly infinite variation of attacks.

To avoid this problem, different approaches exist. Among them, data augmentation consists into extending artificially the set of input data for learning in a realistic way.

Principales activités:

The aim of the postdoc is to assess the effectiveness of data augmentation techniques in enhancing the robustness of attack detection mechanisms based on machine learning classifiers.

Concretely, it consists in extending datasets of network traffic containing attacks and evaluate the accuracy of the ML classifier with the newly generated data (with or without retraining).

In addition to GANs, alternative approaches such as using a well-selected sequence of data transformations, also known as a data augmentation policy, have been explored [5].

In addition, the postdoc will have the opportunity to experiment with other approaches, such as using adversarial autoencoders or Kronecker Graphs.

References
[1] Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville et Yoshua Bengio enerative Adversarial Networks Advances in Neural Information Processing Systems 27, 2014
[2] Yan Zuo, Gil Avraham, Tom Drummond : Generative Adversarial Forests for Better Conditioned Adversarial Learning. CoRR abs/
[3] S. K. Lim, Y. Loo, N. Tran, N. Cheung, G. Roig and Y.

Elovici DOPING :
Generative Data Augmentation for Unsupervised Anomaly Detection with GAN 2018 IEEE International Conference on Data Mining (ICDM)
[4] M. Al Olaimat, D. Lee, Y. Kim, J. Kim and J. Kim A Learning-based Data Augmentation for Network Anomaly Detection th International Conference on Computer Communications and Networks (ICCCN)
[5] E. D. Cubuk, B. Zoph, J. Shlens and Q. V.

Le andaugment :
Practical automated data augmentation with a reduced search space 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Compétences:

Required qualification: PhD in Computer Science
Required knowledge: networking, network security, machine learning including practical experiences with large datasets
Languages: Shell, python, ML libraries and others are appreciated
Fluent in english (writing and oral communication)

Avantages:

Subsidized meals
Partial reimbursement of public transport costs
Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
Professional equipment available (videoconferencing, loan of computer equipment, etc.)
Social, cultural and sports events and activities
Access to vocational training
Social security coverage

Rémunération:

2788€ gross/month

Informations générales:

-
Thème/Domaine: Réseaux et télécommunications

Système & réseaux (BAP E)

-
Ville: Villers lès Nancy

-
Centre Inria: Centre Inria de l'Université de Lorraine
-
Date de prise de fonction souhaitée:
-
Durée de contrat: 2 ans
-
Date limite pour postuler:

Consignes pour postuler:

Sécurité défense:

Ce poste est susceptible d'être affecté dans une zone à régime restrictif (ZRR), telle que définie dans le décret n° relatif à la protection du po