Article
Computer Science, Hardware & Architecture
Ola Salman, Imad H. Elhajj, Ali Chehab, Ayman Kayssi
Summary: Traffic classification is essential for managing network Quality of Service (QoS) and security. This paper proposes an approach for early traffic classification based on empirical assessment and information theory. The study suggests a confidence measure to determine the optimal number of packets to inspect, balancing between response time and classification accuracy. Additionally, an ensemble Deep Learning (DL)-based classifier model is introduced to enhance the accuracy by training successive DL models. The experimental results demonstrate improved early classification accuracy with the proposed measures and ensemble method.
Article
Chemistry, Multidisciplinary
Xiaoyi Ma, Xiaowei Hu, Thomas Weber, Dieter Schramm
Summary: This article discusses the experience of building a simulation scenario of the whole city of Duisburg using real traffic data, highlighting the challenges and time-consuming nature of setting up a realistic traffic scenario. By establishing the simulation scenario in the SUMO software package, four different networks and traffic volumes were compared successfully.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Information Systems
Luiz Fernando Pinto de Oliveira, Leandro Tiago Manera, Paulo Denis Garcez da Luz
Summary: Traffic light control systems have been widely used to monitor and control vehicle flow since their emergence. The increase in public and private vehicles has led to traffic congestion and environmental pollution, prompting large cities to adopt technological solutions for smart cities. Various hardware and software solutions have been studied and implemented globally to improve traffic management systems.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Swati Dhingra, Rajasekhara Babu Madda, Rizwan Patan, Pengcheng Jiao, Kaveh Barri, Amir H. Alavi
Summary: The Internet of Things is transforming the world by connecting billions of physical and virtual objects to the Internet, generating massive amounts of data that may be hard to manage efficiently. An integrated fog and cloud computing framework has been introduced to tackle issues like real-time analytics, latency and network congestion, improving performance in traffic monitoring.
INTERNET OF THINGS
(2021)
Article
Chemistry, Physical
Xiya Yang, Guangqing Liu, Qiyao Guo, Haiyang Wen, Ruiyuan Huang, Xianghe Meng, Jialong Duan, Qunwei Tang
Summary: By utilizing a self-powered triboelectric sensor that uses transferred charge density as sensing signals and carbon nanotube doping to increase sensitivity, the requirements for smart traffic monitoring and management are met. By connecting to cloud IoT services, functions such as traffic flow management, vehicle capturing, and plate number recognition are realized.
Article
Computer Science, Information Systems
Teng Zhan, Shiping Chen
Summary: With the rapid development of network technology, monitoring high-speed network traffic has become crucial. This paper investigates the use and improvement of high-performance hash technology for traffic detection and monitoring in IoT systems. The experimental results show a significant performance improvement with the improved hash technology.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Theory & Methods
Xinchang Zhang, Tianyi Wang
Summary: This article studies a novel bandwidth reservation solution based on distributed traffic monitoring and control to improve service quality for data transfers. By allocating designated bandwidth and dynamically sharing reserved bandwidth resources, resource utilization can be improved and congestion can be effectively eliminated. The article also proposes a solution to the delay-constrained traffic monitoring structure construction problem and a dynamic traffic control algorithm.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2022)
Article
Computer Science, Hardware & Architecture
Anja Feldmann, Oliver Gasser, Franziska Lichtblau, Enric Pujol, Ingmar Poese, Christoph Dietzel, Daniel Wagner, Matthias Wichtlhuber, Juan Tapiador, Narseo Vallina-Rodriguez, Oliver Hohlfeld, Georgios Smaragdakis
Summary: This paper reviews the impact of the first year of the COVID-19 pandemic on Internet traffic and analyzes its performance to understand the new changes and how the Internet responded to these challenges during the unprecedented times.
COMMUNICATIONS OF THE ACM
(2021)
Article
Chemistry, Analytical
Zhoujing Ye, Guannan Yan, Ya Wei, Bin Zhou, Ning Li, Shihui Shen, Linbing Wang
Summary: Traditional road-embedded monitoring systems have limitations, therefore the development of a pavement vibration monitoring system based on IoT is significant. This monitoring system enhances the intelligence of road infrastructure and allows for real-time traffic information acquisition.
Article
Chemistry, Multidisciplinary
Hamza Awad Hamza Ibrahim, Omer Radhi A. L. Zuobi, Awad M. Abaker, Musab B. Alzghoul
Summary: This paper discusses the importance of internet traffic classification and the necessity of hybrid classification methods, proposing a hybrid online classifier system HOC based on two common classification methods. The system demonstrates high accuracy in classifying internet application classes.
APPLIED SCIENCES-BASEL
(2021)
Article
Mathematics
Yunsun Kim, Sahm Kim
Summary: This study found that internet traffic can be a useful variable in short-term electricity demand forecasts, especially in the new multivariate model VARX. Furthermore, the VAR model showed excellent forecasting performance, outperforming the artificial neural network model.
Article
Telecommunications
Tri Gia Nguyen, Trung Phan, Dinh Thai Hoang, Tu N. Nguyen, Chakchai So-In
Summary: DeepMonitor proposes a novel traffic monitoring framework for SDN-based IoT networks, utilizing DDQN algorithm and federated DDQN mechanism to optimize flow table control and learning performance. Through extensive emulations, the results show significant improvements in flow rule match-field control and DDoS attack detection performance compared to existing solutions.
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING
(2021)
Article
Computer Science, Information Systems
David Ponce, Christian Tipantuna, Cristian Espinosa
Summary: This paper presents a comprehensive analysis of Internet traffic growth and behavior in Ecuador, with a focus on the impact of the COVID-19 pandemic. The study examines the concepts of autonomous systems and Internet exchange points, using data provided by AEPROVI. It investigates the distribution of IP addresses, local prefix exchanges, and bit rate capacities used by major ISPs. The study also highlights how the pandemic increased the demand for virtual education and telework, leading to a surge in Internet traffic and the need to upgrade infrastructure.
Article
Computer Science, Information Systems
Davide Andrea Guastella, Evangelos Pournaras
Summary: Smart mobility initiatives aim to improve urban infrastructures and reduce carbon footprint. This paper introduces a privacy-aware method using edge computing to estimate traffic density without deploying privacy-intrusive surveillance technologies. The proposed solution shows better accuracy and lower cost compared to standard prediction methods, offering a potential alternative to massive camera deployment.
Article
Computer Science, Artificial Intelligence
Dunnan Liu, Xiaofeng Xu, Mingguang Liu, Yaling Liu
Summary: With the rapid development of the Internet, network traffic classification has become a hot topic for scientists. The continuous advancement of Internet of Things technology presents new challenges for network traffic classification, where machine learning decision tree classification algorithms have been proven to be efficient and improve network resource utilization.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Greta Vallero, Daniela Renga, Michela Meo, Marco Ajmone Marsan
Summary: This paper focuses on using ML tools for resource management in a portion of a Radio Access Network (RAN), specifically in Base Station (BS) activation and deactivation. The aim is to reduce energy consumption while meeting the variable traffic demand of users. Traffic predictions, made using Artificial Neural Networks (ANN), are used to make informed decisions on BS activation and deactivation. The results indicate that even with prediction errors, good performance trade-offs can be achieved, and dynamic resource allocation has an impact on BS failure rates.
COMPUTER COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Martino Trevisan, Francesca Soro, Marco Mellia, Idilio Drago, Ricardo Morla
Summary: Privacy protection is a priority on the Internet, and various methods have been used to limit personal information leakage. However, domain names are still visible to observers in the network. Efforts have been made to encrypt domain names, but this article shows that simple features and machine learning models can still recover encrypted domain names with high precision and recall. The effectiveness of padding-based mitigation is also evaluated, and it is found that all three attacks can still be successful despite padding. Therefore, more robust techniques are needed to protect end users' privacy.
ACM TRANSACTIONS ON INTERNET TECHNOLOGY
(2023)
Article
Computer Science, Hardware & Architecture
Nikhil Jha, Luca Vassio, Martino Trevisan, Emilio Leonardi, Marco Mellia
Summary: With the rise of big data and data markets, preserving individuals' privacy has become crucial. Anonymization, particularly through k-anonymity, is the traditional approach to address this need. However, achieving k-anonymity becomes difficult in continuous data streams and when dealing with a large number of attributes.
PERFORMANCE EVALUATION
(2023)
Article
Computer Science, Information Systems
Luca Gioacchini, Luca Vassio, Marco Mellia, Idilio Drago, Zied Ben Houidi, Dario Rossi
Summary: Darknets are probes that listen to traffic reaching IP addresses that host no services. This traffic results from the actions of internet scanners, botnets, and misconfigured hosts. i-DarkVec is a methodology that uses Natural Language Processing techniques to learn meaningful representations of darknet traffic. The embeddings learned with i-DarkVec enable various machine learning tasks, such as identifying clusters of senders engaged in similar activities and solving the classification problem of associating unknown sources with coordinated actors. i-DarkVec leverages a scalable and robust incremental embedding learning approach, making it applicable to dynamic and large-scale scenarios.
ACM TRANSACTIONS ON INTERNET TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Ovidiu Iacoboaiea, Jonatan Krolikowski, Zied Ben Houidi, Dario Rossi
Summary: Machine learning is being increasingly used in automating networking tasks, known as zero touch network and service management (ZSM). Deep reinforcement learning (DRL) techniques have gained attention for their ability to make complex decisions across various fields. In the ZSM context, DRL is an attractive approach for tasks like dynamic resource allocation, typically formulated as hard optimization problems. However, training and deploying DRL agents in real-world scenarios face challenges, which are addressed in this article through guidelines focusing on wireless local area network radio resource management.
IEEE COMMUNICATIONS MAGAZINE
(2023)
Article
Computer Science, Information Systems
Alessandro Ciociola, Danilo Giordano, Luca Vassio, Marco Mellia
Summary: This paper analyzes the impact of different demand intensities on system design options for electric vehicle free-floating car sharing systems (EV-FFCS). Data from a car sharing system in three different cities are used to build demand and supply models. The performance of different design options is evaluated from the perspectives of customers and operators in terms of service quality and profitability. The study examines the number and placement of chargers, as well as fleet size. The results highlight the importance of scaling charging infrastructure capacity proportionally to mobility demand and the potential for profitability with increased demand and fleet size.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Hardware & Architecture
Tania Cerquitelli, Michela Meo, Marilia Curado, Lea Skorin-Kapov, Eirini Eleni Tsiropoulou
Summary: This special issue explores how emerging machine learning (ML) and artificial intelligence (AI) algorithms can help computer networks become smarter, aiming to disseminate cutting-edge research findings and advances in computer networks with innovative data-driven methodologies and technologies empowered by ML. The objective is to present effective and promising ML methodologies in the networking context to inspire other researchers and practitioners in the field.
Proceedings Paper
Computer Science, Information Systems
Rodolfo Valentim, Idilio Drago, Marco Mellia, Federico Cerutti
Summary: Sound-squatting is a phishing attack that exploits similarities in the pronunciation of words to deceive users into accessing malicious resources. Defending against this threat is complex and existing solutions are limited in scope. To address this, we introduce Sound-squatter, a multi-language AI-based system that generates sound-squatting candidates for proactive defense, covering a large percentage of exact and approximated homophones.
2023 IEEE EUROPEAN SYMPOSIUM ON SECURITY AND PRIVACY WORKSHOPS, EUROS&PW
(2023)
Proceedings Paper
Computer Science, Hardware & Architecture
Dena Markudova, Michela Meo
Summary: This study proposes ReCoCo, a congestion control solution for RTC applications based on reinforcement learning. By collecting network condition information at the receiver-side and predicting the available bandwidth, it outperforms the GCC algorithm in both specialized and general models.
2023 IEEE 24TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE SWITCHING AND ROUTING, HPSR
(2023)
Proceedings Paper
Engineering, Electrical & Electronic
Zunera Umar, Michela Meo
Summary: Power line communication (PLC) technology allows for broadband access networks in remote areas using existing power infrastructure, with the help of edge servers and devices that improve data processing and reduce network delays, as well as caching technology for efficient data retrieval and storage.
2022 32ND INTERNATIONAL TELECOMMUNICATION NETWORKS AND APPLICATIONS CONFERENCE (ITNAC)
(2022)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Andrea Marin, Michela Meo, Matteo Sereno, Marco Ajmone Marsan
Summary: In this study, we analyze the performance of an access link in a data network loaded with data flows from streaming and elastic services. We introduce a new queuing model and demonstrate that, with the admission control algorithm, the model can express the joint limiting probability distribution of active services of different types as a product form expression. Numerical results reveal unexpected oscillating behaviors in several performance metrics and provide interesting insights into the link performance.
2022 IEEE 23RD INTERNATIONAL SYMPOSIUM ON A WORLD OF WIRELESS, MOBILE AND MULTIMEDIA NETWORKS (WOWMOM 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Matteo Boffa, Giulia Milan, Luca Vassio, Idilio Drago, Marco Mellia, Zied Ben Houidi
Summary: This study evaluates the application of Natural Language Processing (NLP) in honeypot attack activities and successfully uses clustering algorithms to identify attackers' goals. This is of great importance for automatically identifying attack patterns in honeypots and supporting security activities.
7TH IEEE EUROPEAN SYMPOSIUM ON SECURITY AND PRIVACY WORKSHOPS (EUROS&PW 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Thomas Favale, Danilo Giordano, Idilio Drago, Marco Mellia
Summary: This paper revisits the visibility problem of honeypots from a horizontal perspective and deploys a flexible honeypot system to collect and analyze data from multiple services. The study reveals that some attackers focus on a few services while others target multiple services simultaneously. Furthermore, it provides an analysis of brute-force attacks against multiple services.
7TH IEEE EUROPEAN SYMPOSIUM ON SECURITY AND PRIVACY WORKSHOPS (EUROS&PW 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Rodolfo Valentim, Idilio Drago, Federico Cerutti, Marco Mellia
Summary: Domain squatting is an attacking technique that tricks users by exploiting the similarity between domain names, and sound-squatting is a specific type that targets the similarity in pronunciation. With the increasing popularity of intelligent speakers and voice-based navigation, there is a need for better methods to protect users from sound-squatting attacks. In this study, an AI-based approach is proposed to automatically generate sound-squatting candidates using text translation capabilities. The generated candidates are evaluated and classified according to their threat level, demonstrating the usefulness of automatic sound-squatting generation in proactively preventing abuse.
7TH IEEE EUROPEAN SYMPOSIUM ON SECURITY AND PRIVACY WORKSHOPS (EUROS&PW 2022)
(2022)
Proceedings Paper
Computer Science, Information Systems
Greta Vallero, Daniela Renga, Michela Meo
Summary: With advancements in communications technologies and antennas, High Altitude Platforms (HAPS) are now considered a promising aerial network component that can support Radio Access Networks (RANs). Equipped with directional antennas, HAPS can activate beams and provide coverage to a large radius of ground area. By off-loading content requests using a Multi Access Edge Computing (MEC) server, HAPS can bring additional capacity to RANs.
2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC)
(2022)