Modern Security Analytics: Finding a Needle in the Hay Blower

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00226435" target="_blank" >RIV/68407700:21230/14:00226435 - isvavai.cz</a>

Výsledek na webu

<a href="http://ic.epfl.ch/researchday2014-speakers" target="_blank" >http://ic.epfl.ch/researchday2014-speakers</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Modern Security Analytics: Finding a Needle in the Hay Blower

Popis výsledku v původním jazyce

Detection of advanced security threats is one of the exciting problems of current computer science. The field, which has been traditionally considered an art, rather than science, has been undergoing major transformation due to the rapid evolution of attacks staged by government actors and organised crime, rather than the hobbyists and enthusiasts from the past. In order to keep the pace with the attackers, a mix of approaches from machine learning, "big data analytics", game theory and distributed computing is necessary to deliver a robust, scalable and affordable solution to this problem. The talk will concentrate on the stream analytics, i.e. the application of highly efficient machine learning methods to data in flight, prior to their serialisationand more in-depth analytics steps. We will follow one case of malware detection on its path through the system, and we will also shoe that a bit of an art is still necessary to make science work in highly adversarial environment.

Název v anglickém jazyce

Modern Security Analytics: Finding a Needle in the Hay Blower

Popis výsledku anglicky

Detection of advanced security threats is one of the exciting problems of current computer science. The field, which has been traditionally considered an art, rather than science, has been undergoing major transformation due to the rapid evolution of attacks staged by government actors and organised crime, rather than the hobbyists and enthusiasts from the past. In order to keep the pace with the attackers, a mix of approaches from machine learning, "big data analytics", game theory and distributed computing is necessary to deliver a robust, scalable and affordable solution to this problem. The talk will concentrate on the stream analytics, i.e. the application of highly efficient machine learning methods to data in flight, prior to their serialisationand more in-depth analytics steps. We will follow one case of malware detection on its path through the system, and we will also shoe that a bit of an art is still necessary to make science work in highly adversarial environment.

Druh

O - Ostatní výsledky

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/VG20122014079" target="_blank" >VG20122014079: Behaviorální detekce pokročilých útočníků v počítačových sítích</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2014

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů