Deep networks in online malware detection

0512092 - ÚI 2020 RIV DE eng C - Conference Paper (international conference)
Tumpach, J. - Krčál, M. - Holeňa, Martin
Deep networks in online malware detection.
ITAT 2019: Information Technologies – Applications and Theory. Aachen: Technical University & CreateSpace Independent Publishing, 2019 - (Barančíková, P.; Holeňa, M.; Horváth, T.; Pleva, M.; Rosa, R.), s. 90-98. CEUR Workshop Proceeding, 2473. ISSN 1613-0073.
[ITAT 2019: Conference Information Technologies - Applications and Theory /19./. Donovaly (SK), 20.09.2019-24.09.2019]
R&D Projects: GA ČR(CZ) GA18-18080S
Grant - others:GA MŠk(CZ) LM2015042
Institutional support: RVO:67985807
Keywords : artificial neural networks * multilayer perceptrons * deep networks * semi-supervised learning * malware detection
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
http://ceur-ws.org/Vol-2473/paper7.pdf

Deep learning is usually applied to static datasets. If used for classification based on data streams, it is not easy to take into account a non-stationarity. This paper presents work in progress on a new method for online deep classification learning in data streams with slow or moderate drift, highly relevant for the application domain of malware detection. The method uses a combination of multilayer perceptron and variational autoencoder to achieve constant memory consumption by encoding past data to a generative model. This can make online learning of neural networks more accessible for independent adaptive systems with limited memory. First results for real-world malware stream data are presented.
Permanent Link: http://hdl.handle.net/11104/0302298