TY - INPR A1 - Prasse, Paul A1 - Gruben, Gerrit A1 - Machlika, Lukas A1 - Pevny, Tomas A1 - Sofka, Michal A1 - Scheffer, Tobias T1 - Malware Detection by HTTPS Traffic Analysis N2 - In order to evade detection by network-traffic analysis, a growing proportion of malware uses the encrypted HTTPS protocol. We explore the problem of detecting malware on client computers based on HTTPS traffic analysis. In this setting, malware has to be detected based on the host IP address, ports, timestamp, and data volume information of TCP/IP packets that are sent and received by all the applications on the client. We develop a scalable protocol that allows us to collect network flows of known malicious and benign applications as training data and derive a malware-detection method based on a neural networks and sequence classification. We study the method's ability to detect known and new, unknown malware in a large-scale empirical study. KW - machine learning KW - computer security Y1 - 2017 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:517-opus4-100942 ER - TY - JOUR A1 - Kibrik, Andrej A. A1 - Khudyakova, Mariya V. A1 - Dobrov, Grigory B. A1 - Linnik, Anastasia A1 - Zalmanov, Dmitrij A. T1 - Referential Choice BT - Predictability and Its Limits JF - Frontiers in psychology N2 - We report a study of referential choice in discourse production, understood as the choice between various types of referential devices, such as pronouns and full noun phrases. Our goal is to predict referential choice, and to explore to what extent such prediction is possible. Our approach to referential choice includes a cognitively informed theoretical component, corpus analysis, machine learning methods and experimentation with human participants. Machine learning algorithms make use of 25 factors, including referent’s properties (such as animacy and protagonism), the distance between a referential expression and its antecedent, the antecedent’s syntactic role, and so on. Having found the predictions of our algorithm to coincide with the original almost 90% of the time, we hypothesized that fully accurate prediction is not possible because, in many situations, more than one referential option is available. This hypothesis was supported by an experimental study, in which participants answered questions about either the original text in the corpus, or about a text modified in accordance with the algorithm’s prediction. Proportions of correct answers to these questions, as well as participants’ rating of the questions’ difficulty, suggested that divergences between the algorithm’s prediction and the original referential device in the corpus occur overwhelmingly in situations where the referential choice is not categorical. KW - referential choice KW - non-categoricity KW - machine learning KW - cross-methodological approach KW - discourse production Y1 - 2016 U6 - https://doi.org/10.3389/fpsyg.2016.01429 SN - 1664-1078 VL - 7 PB - Frontiers Research Foundation CY - Lausanne ER - TY - GEN A1 - Kibrik, Andrej A. A1 - Khudyakova, Mariya V. A1 - Dobrov, Grigory B. A1 - Linnik, Anastasia A1 - Zalmanov, Dmitrij A. T1 - Referential Choice BT - Predictability and Its Limits N2 - We report a study of referential choice in discourse production, understood as the choice between various types of referential devices, such as pronouns and full noun phrases. Our goal is to predict referential choice, and to explore to what extent such prediction is possible. Our approach to referential choice includes a cognitively informed theoretical component, corpus analysis, machine learning methods and experimentation with human participants. Machine learning algorithms make use of 25 factors, including referent’s properties (such as animacy and protagonism), the distance between a referential expression and its antecedent, the antecedent’s syntactic role, and so on. Having found the predictions of our algorithm to coincide with the original almost 90% of the time, we hypothesized that fully accurate prediction is not possible because, in many situations, more than one referential option is available. This hypothesis was supported by an experimental study, in which participants answered questions about either the original text in the corpus, or about a text modified in accordance with the algorithm’s prediction. Proportions of correct answers to these questions, as well as participants’ rating of the questions’ difficulty, suggested that divergences between the algorithm’s prediction and the original referential device in the corpus occur overwhelmingly in situations where the referential choice is not categorical. T3 - Zweitveröffentlichungen der Universität Potsdam : Humanwissenschaftliche Reihe - 306 KW - cross-methodological approach KW - discourse production KW - machine learning KW - non-categoricity KW - referential choice Y1 - 2016 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:517-opus4-100313 ER - TY - JOUR A1 - Kibrik, Andrej A. A1 - Khudyakova, Mariya V. A1 - Dobrov, Grigory B. A1 - Linnik, Anastasia A1 - Zalmanov, Dmitrij A. T1 - Referential Choice: Predictability and Its Limits JF - Frontiers in psychology N2 - We report a study of referential choice in discourse production, understood as the choice between various types of referential devices, such as pronouns and full noun phrases. Our goal is to predict referential choice, and to explore to what extent such prediction is possible. Our approach to referential choice includes a cognitively informed theoretical component, corpus analysis, machine learning methods and experimentation with human participants. Machine learning algorithms make use of 25 factors, including referent’s properties (such as animacy and protagonism), the distance between a referential expression and its antecedent, the antecedent’s syntactic role, and so on. Having found the predictions of our algorithm to coincide with the original almost 90% of the time, we hypothesized that fully accurate prediction is not possible because, in many situations, more than one referential option is available. This hypothesis was supported by an experimental study, in which participants answered questions about either the original text in the corpus, or about a text modified in accordance with the algorithm’s prediction. Proportions of correct answers to these questions, as well as participants’ rating of the questions’ difficulty, suggested that divergences between the algorithm’s prediction and the original referential device in the corpus occur overwhelmingly in situations where the referential choice is not categorical. KW - referential choice KW - non-categoricity KW - machine learning KW - cross-methodological approach KW - discourse production Y1 - 2016 U6 - https://doi.org/10.3389/fpsyg.2016.01429 SN - 1664-1078 VL - 7 SP - 9939 EP - 9947 PB - Frontiers Research Foundation CY - Lausanne ER - TY - GEN A1 - Hollstein, André A1 - Segl, Karl A1 - Guanter, Luis A1 - Brell, Maximilian A1 - Enesco, Marta T1 - Ready-to-Use methods for the detection of clouds, cirrus, snow, shadow, water and clear sky pixels in Sentinel-2 MSI images T2 - remote sensing N2 - Classification of clouds, cirrus, snow, shadows and clear sky areas is a crucial step in the pre-processing of optical remote sensing images and is a valuable input for their atmospheric correction. The Multi-Spectral Imager on board the Sentinel-2's of the Copernicus program offers optimized bands for this task and delivers unprecedented amounts of data regarding spatial sampling, global coverage, spectral coverage, and repetition rate. Efficient algorithms are needed to process, or possibly reprocess, those big amounts of data. Techniques based on top-of-atmosphere reflectance spectra for single-pixels without exploitation of external data or spatial context offer the largest potential for parallel data processing and highly optimized processing throughput. Such algorithms can be seen as a baseline for possible trade-offs in processing performance when the application of more sophisticated methods is discussed. We present several ready-to-use classification algorithms which are all based on a publicly available database of manually classified Sentinel-2A images. These algorithms are based on commonly used and newly developed machine learning techniques which drastically reduce the amount of time needed to update the algorithms when new images are added to the database. Several ready-to-use decision trees are presented which allow to correctly label about 91% of the spectra within a validation dataset. While decision trees are simple to implement and easy to understand, they offer only limited classification skill. It improves to 98% when the presented algorithm based on the classical Bayesian method is applied. This method has only recently been used for this task and shows excellent performance concerning classification skill and processing performance. A comparison of the presented algorithms with other commonly used techniques such as random forests, stochastic gradient descent, or support vector machines is also given. Especially random forests and support vector machines show similar classification skill as the classical Bayesian method. T3 - Zweitveröffentlichungen der Universität Potsdam : Mathematisch-Naturwissenschaftliche Reihe - 455 KW - Sentinel-2 MSI KW - cloud detection KW - snow detection KW - cirrus detection KW - shadow detection KW - Bayesian classification KW - machine learning KW - decision trees Y1 - 2018 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:517-opus4-407938 ER - TY - CHAP ED - Meinel, Christoph ED - Polze, Andreas ED - Oswald, Gerhard ED - Strotmann, Rolf ED - Seibold, Ulrich ED - Schulzki, Bernhard T1 - HPI Future SOC Lab BT - Proceedings 2016 N2 - The “HPI Future SOC Lab” is a cooperation of the Hasso Plattner Institute (HPI) and industrial partners. Its mission is to enable and promote exchange and interaction between the research community and the industrial partners. The HPI Future SOC Lab provides researchers with free of charge access to a complete infrastructure of state of the art hard and software. This infrastructure includes components, which might be too expensive for an ordinary research environment, such as servers with up to 64 cores and 2 TB main memory. The offerings address researchers particularly from but not limited to the areas of computer science and business information systems. Main areas of research include cloud computing, parallelization, and In-Memory technologies. This technical report presents results of research projects executed in 2016. Selected projects have presented their results on April 5th and November 3th 2016 at the Future SOC Lab Day events. N2 - Das Future SOC Lab am HPI ist eine Kooperation des Hasso-Plattner-Instituts mit verschiedenen Industriepartnern. Seine Aufgabe ist die Ermöglichung und Förderung des Austausches zwischen Forschungsgemeinschaft und Industrie. Am Lab wird interessierten Wissenschaftlern eine Infrastruktur von neuester Hard- und Software kostenfrei für Forschungszwecke zur Verfügung gestellt. Dazu zählen teilweise noch nicht am Markt verfügbare Technologien, die im normalen Hochschulbereich in der Regel nicht zu finanzieren wären, bspw. Server mit bis zu 64 Cores und 2 TB Hauptspeicher. Diese Angebote richten sich insbesondere an Wissenschaftler in den Gebieten Informatik und Wirtschaftsinformatik. Einige der Schwerpunkte sind Cloud Computing, Parallelisierung und In-Memory Technologien. In diesem Technischen Bericht werden die Ergebnisse der Forschungsprojekte des Jahres 2016 vorgestellt. Ausgewählte Projekte stellten ihre Ergebnisse am 5. April 2016 und 3. November 2016 im Rahmen der Future SOC Lab Tag Veranstaltungen vor. KW - Future SOC Lab KW - research projects KW - multicore architectures KW - In-Memory technology KW - cloud computing KW - machine learning KW - artifical intelligence KW - Future SOC Lab KW - Forschungsprojekte KW - Multicore Architekturen KW - In-Memory Technologie KW - Cloud Computing KW - maschinelles Lernen KW - künstliche Intelligenz Y1 - 2016 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:517-opus4-406787 ER -