2020. 2nd Issue
Volume XII, Number 2
Full issue (10,4 MB)
MESSAGE FROM THE GUEST EDITORS
Special Issue on Quality Achievements at BME-VIK with Student Contributions in EFOP-3.6.2-16-013 – Guest Editorial
The project EFOP-3.6.2-16-013, "Thematic Research Collaborations for Innovative Informatics and Infocommunication Solutions" (abbreviated as 3IN) started in September 2017. The abbreviation refers to the three participating institutions, Eötvös Loránd University (ELTE), Budapest University of Technology and Economics (BME), and Pázmány Péter Catholic University (PPKE), and to the three innovation areas in focus: Software Development and Information Security (A / Pillar), Infocommunication Networks and Cyberphysical Systems (B / Pillar) and Intelligent Data Analysis (C / Pillar).
Csaba Simon, Markosz Maliosz, Miklós Máté, Dávid Balla and Kristóf Torma
Sidecar based resource estimation method for virtualized environments
The widespread use of virtualization technologies in telecommunication system resulted in series of benefits, as flexibility, agility and increased resource usage efficiency. Nevertheless, the use of Virtualized Network Functions (VNF) in virtualized modules (e.g., containers, virtual machines) also means that some legacy mechanisms that are crucial for a telco grade operation are no longer efficient. Specifically, the monitoring of the resource sets (e.g., CPU power, memory capacity) allocated to VNFs cannot rely anymore on the methods developed for earlier deployment scenarios. Even the recent monitoring solutions designed for cloud environments is rendered useless if the VNF vendor and the telco solution supplier has to deploy its product into a virtualized environment, since it does not have access to the host level monitoring tools. In this paper we propose a sidecar-based solution to evaluate the resources available for a virtualized process. We evaluated the accuracy of our proposal in a proof of concept deployment, using KVM, Docker and Kubernetes virtualization technologies, respectively. We show that our proposal can provide real monitoring data and discuss its applicability.
Ádám Marosits, Ágoston Schranz and Eszter Udvary
Amplified spontaneous emission based quantum random number generator
There is an increasing need for true random bits, for which true random number generators (TRNG) are absolutely necessary, because the output of pseudo random number generators is deterministically calculated from the previous states. We introduce our quantum number generator (QRNG) based on amplified spontaneous emission (ASE), a truly random quantum physical process. The experimental setup utilizes the randomness of the process. In this system, optical amplifiers (based on ASE) play the major role. The suitable sampling rate is selected in order to build the fastest generator, while avoiding the correlation between consecutive bits. Furthermore, the applied post-processing increases the quality of the random bits. As a results of this, our system generated random bits which successfully passed the NIST tests. Our real-time generation system – which is currently a trial version implemented with cheap equipment – will be available for public use, generating real time random bits using a web page.
David Kobor and Eszter Udvary
Optimisation of Optical Network for Continuous-Variable Quantum Key Distribution by Means of Simulation
The unprecedented breakthrough in the field of quantum computing in the last several years is threatening with the exploitation of our current communication systems. To address this issue, researchers are getting more involved in finding methods to protect these systems. Amongst other tools, quantum key distribution could be a potentially applicable way to achieve the desired level of protection. In this paper we are evaluating the physical layer of an optical system realising continuous variable quantum key distribution (CVQKD) with simulations to determine its weak points and suggest methods to improve them. We found that polarisation dependent devices are crucial for proper operation, therefore we determined their most defining parameters from the point of operation and suggested extra optical devices to largely improve transmission quality. We also paid attention to polarisation controlling in these sort of systems. Our findings could be valuable as practical considerations to construct reliable CVQKD optical transmission links.
Gergő Ládi, Levente Buttyán and Tamás Holczer
GrAMeFFSI: Graph Analysis Based Message Format and Field Semantics Inference For Binary Protocols, Using Recorded Network Traffic
Protocol specifications describe the interaction between different entities by defining message formats and message processing rules. Having access to such protocol specifications is highly desirable for many tasks, including the analysis of botnets, building honeypots, defining network intrusion detection rules, and fuzz testing protocol implementations. Unfortunately, many protocols of interest are proprietary, and their specifications are not publicly available. Protocol reverse engineering is an approach to reconstruct the specifications of such closed protocols. Protocol reverse engineering can be tedious work if done manually, so prior research focused on automating the reverse engineering process as much as possible. Some approaches rely on access to the protocol implementation, but in many cases, the protocol implementation itself is not available or its license does not permit its use for reverse engineering purposes. Hence, in this paper, we focus on reverse engineering protocol specifications relying solely on recorded network traffic. More specifically, we propose GrAMeFFSI, a method based on graph analysis that can infer protocol message formats as well as certain field semantics for binary protocols from network traces. We demonstrate the usability of our approach by running it on packet captures of two known protocols, Modbus and MQTT, then comparing the inferred specifications to the official specifications of these protocols.
Dávid Papp, Zsolt Knoll and Gábor Szűcs
Graph construction with condition-based weights for spectral clustering of hierarchical datasets
Most of the unsupervised machine learning algorithms focus on clustering the data based on similarity metrics, while ignoring other attributes, or perhaps other type of connections between the data points. In case of hierarchical datasets, groups of points (point-sets) can be defined according to the hierarchy system. Our goal was to develop such spectral clustering approach that preserves the structure of the dataset throughout the clustering procedure. The main contribution of this paper is a set of conditions for weighted graph construction used in spectral clustering. Following the requirements – given by the set of conditions – ensures that the hierarchical formation of the dataset remains unchanged, and therefore the clustering of data points imply the clustering of point-sets as well. The proposed spectral clustering algorithm was tested on three datasets, the results were compared to baseline methods and it can be concluded the algorithm with the proposed conditions always preserves the hierarchy structure.
Csongor Pilinszki-Nagy and Bálint Gyires-Tóth
Performance Analysis of Sparse Matrix Representation in Hierarchical Temporal Memory for Sequence Modeling
Hierarchical Temporal Memory (HTM) is a special type of artificial neural network (ANN), that differs from the widely used approaches. It is suited to efficiently model sequential data (including time series). The network implements a variable order sequence memory, it is trained by Hebbian learning and all
of the network’s activations are binary and sparse. The network consists of four separable units. First, the encoder layer translates the numerical input into sparse binary vectors. The Spatial Pooler performs normalization and models the spatial features of the encoded input. The Temporal Memory is responsible for learning the Spatial Pooler’s normalized output sequence. Finally, the decoder takes the Temporal Memory’s outputs and translates it to the target. The connections in the network are also sparse, which requires prudent design and implementation. In this paper a sparse matrix implementation is elaborated, it is compared to the dense implementation. Furthermore, the HTM’s performance is evaluated in terms of accuracy, speed and memory complexity and compared to the deep neural network-based LSTM (Long Short-Term Memory).
István Fábián and Gábor György Gulyás
De-anonymizing Facial Recognition Embeddings
Advances of machine learning and hardware getting cheaper resulted in smart cameras equipped with facial recognition becoming unprecedentedly widespread worldwide. Undeniably, this has a great potential for a wide spectrum of uses, it also bears novel risks. In our work, we consider a specific related risk, one related to face embeddings, which are machine learning created metric values describing the face of a person. While embeddings seems arbitrary numbers to the naked eye and are hard to interpret for humans, we argue that some basic demographic attributes can be estimated from them and these values can be then used to look up the original person on social networking sites. We propose an approach for creating synthetic, life-like datasets consisting of embeddings and demographic data of several people. We show over these ground truth datasets that the aforementioned re-identifications attacks do not require expert skills in machine learning in order to be executed. In our experiments, we find that even with simple machine learning models the proportion of successfully re-identified people vary between 6.04% and 28.90%, depending on the population size of the simulation.
Levente Alekszejenkó and Tadeusz Dobrowiecki
Adapting IT Algorithms and Protocols to an Intelligent Urban Traffic Control
Autonomous vehicles, communicating with each other and with the urban infrastructure as well, open opportunity to introduce new, complex and effective behaviours to theintelligent traffic systems. Such systems can be perceived quite naturally as hierarchically built intelligent multi-agent systems, with the decision making based upon well-defined and profoundly tested mathematical algorithms, borrowed e.g. from the field of information technology. In this article, two examples of how to adapt such algorithms to the intelligent urban traffic are presented. Since the optimal and fair timing of the traffic lights is crucial in the traffic control, we show how a simple Round-Robin scheduler and Minimal Destination Distance First scheduling (adaptation of the theoretically optimal Shortest Job First scheduler) were implemented and tested for traffic light control. Another example is the mitigation of the congested traffic using the analogy of the Explicit Congestion Notification (ECN) protocol of the computer networks. We show that the optimal scheduling based traffic light control can handle roughly the same complexity of the traffic as the traditional light programs in the nominal case. However, in extraordinary and especially fastly evolving situations, the intelligent solutions can clearly outperform the traditional ones. The ECN based method can successfully limit the traffic flowing through bounded areas. That way the number of passing-through vehicles in e.g. residential areas may be reduced, making them more comfortable congestion-free zones in a city.
Dóra Varnyú and László Szirmay-Kalos
Comparison of Non-Linear Filtering Methods for Positron Emission Tomography
As a result of the limited radiotracer dose, acquisition time and scanner sensitivity, positron emission tomography (PET) images suffer from high noise. In the current clinical practice, post-reconstruction filtering has become one of the most common noise reduction techniques. However, the range of existing filters is very wide, and choosing the most suitable filter for a given measurement is far from simple. This paper aims to provide assistance in this choice by comparing the most powerful image denoising filters, covering both image quality and execution time. Emphasis is placed on non-linear techniques due to their ability to preserve edges and fine details more accurately than linear filters. The compared methods include the Gaussian, the bilateral, the guided, the anisotropic diffusion and the non-local means filters, which are examined in both static and dynamic PET reconstructions.
CALL FOR PAPERS
17th IFIP/IEEE International Symposium on Integrated Network and Service Management
IEEE IM 2021, Bordeaux, France
IEEE International Conference on Communications
IEEE ICC 2021, Montreal, QC, Canada