Discriminative Models for Multi-instance Problems with Tree Structure

0463379 - ÚTIA 2017 RIV US eng C - Conference Paper (international conference)
Somol, Petr - Pevný, T.
Discriminative Models for Multi-instance Problems with Tree Structure.
Proceedings of the 9th ACM Workshop on Artificial Intelligence and Security 2016. New York: ACM, 2016. ISBN 978-1-4503-4573-6.
[9th ACM Workshop on Artificial Intelligence and Security. Vienna (AT), 28.10.2016]
Institutional support: RVO:67985556
Keywords : Neural netwrok * User modeling * Malware detection * Big data * Learning indicators of compromise
Subject RIV: IN - Informatics, Computer Science
http://library.utia.cas.cz/separaty/2016/RO/somol-0463379.pdf

Modelling network traffic is gaining importance to counter modern security threats of ever increasing sophistication. It is though surprisingly difficult and costly to construct reli­able classifiers on top of telemetry data due to the variety and complexity of signals that no human can manage to interpret in full. Obtaining training data with sufficiently large and variable body of labels can thus be seen as a pro­hibitive problem. The goal of this work is to detect infected computers by observing their HTTP(S) traffic collected from network sensors, which are typically proxy servers or net­work firewalls, while relying on only minimal human input in the model training phase. We propose a discriminative model that makes decisions based on a computer’s all traf­.c observed during a predefined time window (5 minutes in our case).
Permanent Link: http://hdl.handle.net/11104/0263127