Offers “CEA”

Expires soon CEA

Research in Detection of cyber-attacks in a smart multisensor embedded system for soil monitoring H/F (Mathématiques, information  scientifique, logiciel)

  • Internship
  • France
  • Administration

Job description

Domaine : Mathématiques, information  scientifique, logiciel

Contrat : Post-doctorat

Description du poste :

Description
The person will be part of a multi-disciplinary team with experts in embedded software, cyber-security for the Internet-of-Things, hardware design, and machine learning.
The work will be part of the H2020 project SARMENTI (Smart multisensor embedded and secure system for soil nutrient and gaseous emission monitoring). The objective of SARMENTI is to develop and validate portable low power multisensor systems connected to the cloud to make in situ soil nutrients analysis and to provide decision support to the farmers by monitoring soil fertility in real-time. The post-doc is concerned with the application of machine learning methods to detect potential cyber-security attacks, and the development of these methods on the multisensory system.
Topic:cyber-attacks increasingly target the connected sensors&actuators employed in various domains such as agriculture. Logical attacks can be combined with physical attacks, constituting very complex attacks for which existing countermeasures are not sufficient. These devices are resource constraint and low cost, e.g., embed small processors cores, and hence cannot include strong security primitives. Supervised machine learning (ML) methods have the potential to detect abnormal behavior, resulting from such attacks, at a low cost. These methods should be embedded close to the processor core, and be easily programmed so that they can fit a given application, such as the soil monitoring.
This project aims at the investigation and demonstration of ML-based detection methods in an embedded system. The main tasks are:
-Familiarise herself/himself with the embedded system platform, namely processor (e.g., RISC-V, ARM), tools, such us the compiler, linker, and simulator. Get acquainted with the state-of-the-art on the simulation of typical attacks for connected device in agriculture, e.g., physical attacks, memory attacks.
-Extend the project platform with modules to trace events the execution of the core, e.g., including performance counters, register access, bus events. This trace will represent a learning base for the ML method.
-Investigate a detection module in the simulator. The underlying algorithm will be based on anomaly detection, e.g., one-class classifier. This work has tree parts, implement the probes that monitor selected events, the communication infrastructure that connects the probes with the detector, and the detector itself.
-Demonstrate the detection features on the SARMENTI prototype, i.e., a smart multisensor embedded system for soil monitoring, developed by European partners.
Experiment and evaluate the cost of the implementation, in terms of computing power and memory footprint, as well as its performance, in terms of false positives, false negatives, etc.
Document and present the work. We aim for publications in international workshops, conferences, and journals. Furthermore the postdoc will learn to work in a joint European project, e.g., collaborate with internat


The candidates should have a Phd and a Master degree in computer science or electronics, and should demonstrate a strong expertise in in embedded systems, , tools and programming environments, e.g., C/C++, Python, ARM development tools, and knowledge in computer architecture.

Langue / Niveau :

Français : Notions

Langue / Niveau :

Anglais : Courant

Make every future a success.
  • Job directory
  • Business directory