Octavian Grigorescu, Alexandra Minea, Tiberiu Dumitru, R. Rughinis
{"title":"Probability and Attack Graph models in Contextual Risk Scoring System","authors":"Octavian Grigorescu, Alexandra Minea, Tiberiu Dumitru, R. Rughinis","doi":"10.1109/RoEduNet57163.2022.9921100","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921100","url":null,"abstract":"The interest of attackers is expanding in response to the on-growing enthusiasm for rapid development, so seeking ways to quantify and manage the risks has become a priority. However, in the current context, there is no consistent and effective strategy for evaluating computer network security. Therefore, we propose a comprehensive software solution that collects, processes, and evaluates data from devices inside a network, in order to identify the key security issues and measure the level of risk using a probability-based model. The final result is represented by the network score, which is a measure of the risk to which it is exposed.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129938098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Buzura, Alis Suciu, E. Cebuc, B. Iancu, V. Dădârlat
{"title":"Development Framework for Simulating Routing Behavior in Software-Defined Wireless Networks","authors":"S. Buzura, Alis Suciu, E. Cebuc, B. Iancu, V. Dădârlat","doi":"10.1109/RoEduNet57163.2022.9921101","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921101","url":null,"abstract":"Wireless technologies play an important role in the Internet of Things (IoT) and they facilitate the deployment of various types of sensor networks. Nodes in a sensor network don’t always have a direct connection to the central sink node, therefore they route packets through other nodes in the network. In the emerging Software-Defined Networking (SDN) architecture, a main controller is responsible for coordinating the network functions including the routing operation. The current article presents a Java-based simulation framework developed for testing the routing mechanism in a wireless SDN. The goal of the implemented framework is to create a working framework that can be used to perform various routing simulations. The framework is constructed to be multi-purpose, it can be used on a local machine, but is also compatible with the Mininet-WiFi network simulator. Routing simulations are performed locally and in Mininet-WiFi on IPv4 networks and they prove the framework’s functionality and its working features.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130003749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Image-based Fruit Recognition and Classification","authors":"Alexandru Marin, I. Radoi","doi":"10.1109/roedunet57163.2022.9921050","DOIUrl":"https://doi.org/10.1109/roedunet57163.2022.9921050","url":null,"abstract":"Automatically analysing images enables a range of applications in the field of agriculture, where many decisions are made based on the appearance of the product. There are significant benefits in the automation of these decisions. An important class of problems, which has seen significant attention in recent years is the analysis of agricultural images such as fruits and vegetables for recognition and classifications purposes. This paper proposes solution that uses Convolutional Neural Networks for classifying fruits as either healthy or damaged. The algorithm was built on YOLOv3, a state-of-the-art network for objects detection in images that runs on the Darknet architecture. The network was trained and evaluated on a newly collected and annotated dataset of over 400 images of 12 different fruits. The algorithm obtained a good classification accuracy of over 75%, considering the 12 double-state classes. We make the collected dataset available together with annotations indicating the type of fruit and the healthy or damaged state.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133158261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cristian Contasel, Dumitru-Cristian Tranca, A. Pălăcean
{"title":"Increasing the security of web applications by using smartphones","authors":"Cristian Contasel, Dumitru-Cristian Tranca, A. Pălăcean","doi":"10.1109/roedunet57163.2022.9921098","DOIUrl":"https://doi.org/10.1109/roedunet57163.2022.9921098","url":null,"abstract":"The web applications security systems often use the authentication strategy and credentials to assess the identity of the user. Based on the credentials, the system is able to claim the identity of the user. Also, the authenticity of identity is claimed based on authentication strategy. This paper analyzes and compares different strategies used to enforce the web applications security systems by using location and biometric features of the smartphones to provide two-way authentications.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130871656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cristian Contasel, Dumitru-Cristian Tranca, A. Pălăcean, D. Rosner
{"title":"Increasing communication security for Bluetooth Medical Devices in eHealth systems","authors":"Cristian Contasel, Dumitru-Cristian Tranca, A. Pălăcean, D. Rosner","doi":"10.1109/roedunet57163.2022.9921104","DOIUrl":"https://doi.org/10.1109/roedunet57163.2022.9921104","url":null,"abstract":"The market of Medical Devices has an annual growth rate perspective of 5.4% in the 2022 – 2028 period. The growth rate is mainly supported by the increased usage of devices for chronic diseases prevention and for remote patient monitoring. The growth rate is also supported by the population’s appetite for mobile devices. The continuously growing number of mobile devices has led to an increase in the number of cyber-attacks against them. In this paper we present Personal Medical Hub, an optimized security solution for Bluetooth enabled medical devices, that enhances data privacy and is aimed to offer protection against man-in-the-middle attacks and other security breaches and backdoors.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129142274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alexandra Sauchea, S. Buzura, A. Peculea, E. Cebuc, V. Dădârlat
{"title":"Open Source Network Management System Based on SharpPcap for QoS and Security Policies","authors":"Alexandra Sauchea, S. Buzura, A. Peculea, E. Cebuc, V. Dădârlat","doi":"10.1109/RoEduNet57163.2022.9921027","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921027","url":null,"abstract":"A network management system (NMS) is a vital tool to be used in a corporate network. It ensures that Quality of Service (QoS) policies are correctly applied, but can also have a great impact over the network security preventing attacks and blocking the ongoing actions of attackers in enterprise networks. The current work presents an implementation of an out-of-band NMS with the primary purpose of detecting and blocking ongoing Domain Name System (DNS) exfiltration attacks which are triggered by other hosts in the network. The secondary purpose of the NMS is to adjust the QoS policies of the other devices in the network manipulating the value of the DifferentiatedServices (DiffServ) field of the IP packets. The solution is implemented using the SharpPcap framework for automated packet processing with the desire to make this system open source for further development. An experimental setup was created using a wiretap for traffic duplication to an out-of-band monitoring device. The experimental work proves that the solution is effective in detecting dictionary-based DNS exfiltration attacks and is successful in blocking the attacker from the network.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124592276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Bootstrapping Road Sign Detection for Self-Driving Cars using Weakly-Supervised Learning","authors":"Costin Rachieru, Adrian Cosma, I. Radoi","doi":"10.1109/RoEduNet57163.2022.9921011","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921011","url":null,"abstract":"Given the escalating trend in the number of cars on the public roads, advanced autonomous driver-assistance systems become more accessible to the masses in order to keep safe traffic participants. This work addresses the problem of traffic signs detection constrained by running in a minimal embedded platform. Our solution consists of the generation of a synthetic object detection dataset using CARLA Simulator, a popular self-driving car virtual environment, enhancing it with image augmentation policies and bootstrapping the model performance by using knowledge distillation from a model ensemble. We make use of modern weakly supervised techniques to minimize labelling noise and achieve a fast, predictive, high-precision model that performs well in real-life scenarios, having a mean average precision of over 53%. The model is integrated with ease into real-time applications achieving 19 FPS on our embedded platform that uses a small size Coral Edge TPU USB Accelerator. Our proposed computer vision solution that powered a scaled self-driving car enabled the team to rank third in the Bosch Future Mobility Challenge 2022, an IEEE ITSS certified contest that encourages the development of complete autonomous driving solutions for scaled vehicles in controlled real-life scenarios.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123648027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Automation of Network Traffic Monitoring using Docker images of Snort3, Grafana and a custom API","authors":"Levente Manases, Daniel Zinca","doi":"10.1109/RoEduNet57163.2022.9921063","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921063","url":null,"abstract":"In this paper we present a mechanism to automate network traffic monitoring by using Docker images. The application has three parts: a Snort3 application for capturing network traffic, a Grafana application to display statistics on the dashboard and a custom API that makes the connection between Snort3 and Grafana. We pushed these images to DockerHub. An automation script, that executes all needed steps, was created and published to a Github repository.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121284348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Web Application for Monitoring Large-scale Virtualized Computing Resources","authors":"R. Poenaru","doi":"10.1109/RoEduNet57163.2022.9921106","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921106","url":null,"abstract":"The Flask framework is used for implementing a simple web app that allows any user to visualize and monitor computing resources that it has access to. The resources are virtualized, deployed, and managed through the OpenStack infrastructure. Within the web app, the user can see the entire set of virtual machines as a topological view or check system information as graphical representations (i.e., pie charts, histograms, and bar charts with machine status, network information, system metrics, and so on). These features can help any scientist dealing with complex simulations that require computational power, by granting a quick way of checking potential issues on the machines executing calculations.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132164835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The Role of Load Balancer Mechanisms in Securing IoT Platforms","authors":"Daniel-Florin Hrițcan, D. Balan","doi":"10.1109/RoEduNet57163.2022.9921059","DOIUrl":"https://doi.org/10.1109/RoEduNet57163.2022.9921059","url":null,"abstract":"As IoT ecosystems are growing these days, the question of potentially dangerous and even life-threatening security risks raises concerns, especially for bigger-scale environments, such as smart cities. In this regard, many cyber security researchers are trying to develop solutions, which eventually could provide a high-security level enough to discourage any attempts of illicit activities. This paper introduces existing technologies, some even at the enterprise level, and more common ones, which could provide a very strong layer of security for web-based monitoring and management platforms used in IoT environments.","PeriodicalId":302692,"journal":{"name":"2022 21st RoEduNet Conference: Networking in Education and Research (RoEduNet)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129742862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}