Research Associate – Causal modeling for Cybersecurity

SnT is a leading international research and innovation centre in secure, reliable and trustworthy ICT systems and services. We play an instrumental role in Luxembourg by fueling innovation through research partnerships with industry, boosting R&D investments leading to economic growth, and attracting highly qualified talent.

The Centre is rapidly expanding its research activities and is seeking highly motivated doctoral candidates who wish to pursue research in close cooperation with our partners. For further information you may check: www.securityandtrust.lu and https://wwwen.uni.lu/snt/research/finatrax

We’re looking for people driven by excellence, excited about innovation, and looking to make a difference. If this sounds like you, you’ve come to the right place!

The SnT is seeking a Postdoc (Research Associate) to support the research and development work within the SEDAN group. We seek a candidate with expertise and/or interest in the following relevant fields: machine learning, statistics, cybersecurity, networking, systems and micro-service architectures. While covering all these expertise fields is not mandatory, we expect the candidate to have strong interest in investigating all of them during the postdoc.

The candidate will the opportunity to work on a CORE project funded by the Luxembourg National Research Fund (FNR) to explore and validate theoretical research. The main objective of the project is to build a cybersecurity-oriented telemetry framework capturing and modeling causal dependencies in a microservice-based infrastructure to identify the complex inter-dependencies among events generated by applications, services, system and network communications.

Going beyond time-series model, the aim of the project is to progress on causal inference [1] modeling by combining probabilistic reasoning [2] and deep learning models [3]. The objective is thus to have a model capable to reason under uncertainty. Therefore, the postdoc will need to define a language for modeling purposes and with a first set of necessary algorithms for learning and inference from events. In a second stage, incremental learning will be considered to update model when drift is detected and merge multiple models. The main application is to discover dependencies in various logs in a micro-service environment (kubernetes) which will be used to track anomalies forward and backward in time. It is thus expected that the successful candidate will also deploy a small environment with existing tools (Prometheus, Loki, cAdvisor, Falco for example) and possibly develop new tools if needed.

In addition, the candidate will be also involved in project management, reporting and dissemination. The project is an academic project oriented but applied research. It is a unique opportunity to develop new concepts with a close collaboration. The project team is composed of the proncipal investigator (Dr. Jérôme FRANCOIS) and two research associates.

During postdoc, the candidate will have the opportunity to participate and propose other projects within the group. We are working on various topics related to applied ML and cyber-security, including applications and security of LLMs.

[1] Judea Pearl, Madelyn Glymour, and Nicholas P Jewell. Causal inference in statistics: A primer. John Wiley & Sons, 2016

[2] De Raedt, L., Kimmig, A. Probabilistic (logic) programming concepts. Mach Learn 100, 5–47 (2015)

[3] Manhaeve, S. Dumancic, A. Kimmig, et al. DeepProbLog: Neural Probabilistic Logic Programming. Conference on Neural Information Processing Systems (NeurIPS), 2018

For further information, please contact us at jerome [dot] francois [at] uni [dot] lu

The candidate should possess a PhD degree in Computer Science/engineering or Telecommunication Engineering,

What we’re looking for:

• A collaborative team player with a desire to make a personal impact within our interdisciplinary research group
• A motivated candidate who can work independently and efficiently and is proactive in solving problems
• Self-initiative, creativity, curiosity, flexibility and enthusiasm to work

Knowledge and Experience:

The ideal candidate should have some knowledge and/or experience in one or several of the following areas:

• Good understanding of the different ML algorithms and architectures
• Good knowledge in statistics and stochastic models
• Good programming skills
• Comfortable with Linux environments

The following qualifications of the applicant are a bonus:

• Experience in micro-services / kubernetes
• Experience in cyber-security
• Good knowledge of networks and systems (protocols, monitoring, management for example)

Language Skills: Fluent written and verbal communication skills in English are required. Knowledge of either French, German or Luxembourgish will be appreciated but are not a requirement to apply.

• Exciting infrastructures and unique labs. At SnT’s two campuses, our researchers can take a walk on the moon at the LunaLab, build a nanosatellite, or help make autonomous vehicles even better
• The right place for IMPACT. SnT researchers engage in demand-driven projects. Through our Partnership Programme, we work on projects with more than 55 industry partners
• Be part of a multicultural family. At SnT we have more than 60 nationalities. Throughout the year, we organise team-building events, networking activities and more