<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
Dear colleagues,<br>
<br>
Three positions in network security are open at Inria Nancy Grand
Est in France:<br>
<br>
<b>1) PhD Position: Hybrid Neural Networks for Anomaly Detection in
Cyber Physical Systems</b><br>
<br>
Recently, machine learning and deep learning algorithms are applied
to detect such anomalies and attacks. However, most of the applied
methods only rely on the cyber part of these systems and on the data
that describe their behavior without considering their physical
models. The PhD candidate will investigate how to employ hybrid
machine learning technique, in particular to apply neural networks
to detect anomalies in CPS while considering its physical model.<br>
<br>
Details and application: <a class="moz-txt-link-freetext"
href="https://jobs.inria.fr/public/classic/fr/offres/2020-02466"
moz-do-not-send="true">https://jobs.inria.fr/public/classic/fr/offres/2020-02466</a><br>
<br>
<b>2) Postdoc: AI-guided assessment of IoT security</b><br>
<br>
The goal of the project is to automatically prevent intrusions by
identifying IoT devices, extract relevant information about their
vulnerabilities and assess the overall risk. We can thus summarize
the global process as follows: (1) identification of the IoT
deployment through topology discovery and fingerprinting, (2)
mapping vulnerability to atomic elements of the IoT deployment based
on public documentations (3) evaluation of the overall risk.<br>
<br>
Details and application: <a class="moz-txt-link-freetext"
href="https://jobs.inria.fr/public/classic/fr/offres/2020-02463"
moz-do-not-send="true">https://jobs.inria.fr/public/classic/fr/offres/2020-02463</a><br>
<br>
<b>3) Postdoc: Automated configuration of network security in
Industrial Control Systems</b><br>
<br>
<span lang="en-US">With the evolution of ICSs highlighted below such
as the integration of many (IoT) devices in smart environments,
their complexity make the full knowledge of normal communications
almost impossible. In particular, it may also depend of the system
states or external events even in the case of M2M communications.
Therefore, the objective of the postdoc is to propose and evaluate
new solutions that will automatically learn profile of M2M
communications in a first step by using different techniques (such
as machine learning) before transforming them into dynamic SDN
policies.<br>
<br>
</span>Details and application: <a class="moz-txt-link-freetext"
href="https://jobs.inria.fr/public/classic/fr/offres/2020-02462"
moz-do-not-send="true">https://jobs.inria.fr/public/classic/fr/offres/2020-02462</a><br>
<b><br>
</b><b>Contacts for all positions: <a
class="moz-txt-link-abbreviated"
href="mailto:jerome.francois@inria.fr" moz-do-not-send="true">jerome.francois@inria.fr</a>
and <a class="moz-txt-link-abbreviated"
href="mailto:abdelkader.lahmadi@loria.fr" moz-do-not-send="true">abdelkader.lahmadi@loria.fr</a></b><br>
<br>
<br>
Jérôme François<br>
Inria Nancy Grand Est<br>
RESIST research team<br>
<a class="moz-txt-link-freetext"
href="https://team.inria.fr/resist/" moz-do-not-send="true">https://team.inria.fr/resist/</a><br>
<span lang="en-US"></span>
</body>
</html>