Number of the records: 1
Discriminative models for multi-instance problems with tree-structure
- 1.
SYSNO ASEP 0507120 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Discriminative models for multi-instance problems with tree-structure Author(s) Pevný, T. (CZ)
Somol, Petr (UTIA-B) RIDNumber of authors 2 Source Title Proceedings of the 2016 ACM Workshop on Artificial Intelligence and Security (AISec'16). - New York : ACM, 2016 - ISBN 978-1-4503-4573-6 Pages s. 83-91 Number of pages 9 s. Publication form Print - P Action the 2016 ACM Workshop on Artificial Intelligence and Security (AISec'16) Event date 28.10.2016 - 28.10.2016 VEvent location Vienna Country AT - Austria Event type WRD Language eng - English Country US - United States Keywords big data ; learning indicators of compromise ; malware detection ; neural network ; user modeling Subject RIV BC - Control Systems Theory OECD category Automation and control systems Institutional support UTIA-B - RVO:67985556 UT WOS 000391051600008 EID SCOPUS 85001945953 DOI 10.1145/2996758.2996761 Annotation 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 traffic observed during a predefined time window (5 minutes in our case). The model is trained on traffic samples collected over equally-sized time windows for a large number of computers, where the only labels needed are (human) verdicts about the computer as a whole (presumed infected vs. presumed clean). As part of training, the model itself learns discriminative patterns in traffic targeted to individual servers and constructs the final high-level classifier on top of them. We show the classifier to perform with very high precision, and demonstrate that the learned traffic patterns can be interpreted as Indicators of Compromise. We implement the discriminative model as a neural network with special structure reflecting two stacked multi instance problems. The main advantages of the proposed configuration include not only improved accuracy and ability to learn from gross labels, but also automatic learning of server types (together with their detectors) that are typically visited by infected computers. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2020
Number of the records: 1