TY - CHAP AU - Orosz, Péter AU - Marosits, Tamás AU - Skopkó, Tamás ED - Varga, Pál ED - Čeleda, Pavel ED - Wauters, Tim ED - Tortonesi, Mauro ED - François, Jérôme ED - Jiménez Galán, Jaime TI - NAPlr: Multi-Gigabit Internet Access Profiling in Web Browser T2 - 2024 20th International Conference on Network and Service Management (CNSM) PB - International Federation for Information Processing (IFIP) CY - Laxenburg SN - 9798331505158 T3 - International Conference on Network and Service Management, ISSN 2165-9605 PY - 2024 PG - 3 DO - 10.23919/CNSM62983.2024.10814449 UR - https://m2.mtmt.hu/api/publication/35760125 ID - 35760125 N1 - Export Date: 14 February 2025; Cited By: 0; Correspondence Address: P. Orosz; Budapest University of Technology and Economics, Dept. of Telecommunications and Artificial Intelligence, Budapest, Hungary; email: orosz@tmit.bme.hu; Conference name: 20th International Conference on Network and Service Management, CNSM 2024; Conference date: 28 October 2024 through 31 October 2024; Conference code: 205683 AB - Advancements in internet service provision have enabled subscribers to access multi-gigabit throughput for both wired and mobile connections. Despite underutilization, users demand compliance with subscription parameters, necessitating precise measurement of multi-gigabit connections. This paper investigates the challenges associated with profiling multi-gigabit internet access using web browsers, addressing limitations introduced by browser capabilities, client hardware, and SOHO router performance. We present a novel measurement system designed to accurately evaluate key service quality parameters, including throughput, latency, and packet loss, for multi-gigabit connections. The system architecture comprises user endpoint devices and measurement servers strategically positioned in high-bandwidth, network-neutral locations to ensure accurate and scalable measurements. Empirical results demonstrate the system's efficacy in measuring multi-gigabit connections, even within the constraints of client and network hardware limitations. This research establishes a robust framework for reliable and comprehensive assessment of high-speed internet access services, contributing to improved service quality and user satisfaction. © 2024 IFIP. LA - English DB - MTMT ER - TY - CHAP AU - Orosz, Péter AU - Marosits, Tamás AU - Skopkó, Tamás ED - Varga, Pál ED - Čeleda, Pavel ED - Wauters, Tim ED - Tortonesi, Mauro ED - François, Jérôme ED - Jiménez Galán, Jaime TI - Assessing Application-Level Network Neutrality using Digital Twins T2 - 2024 20th International Conference on Network and Service Management (CNSM) PB - International Federation for Information Processing (IFIP) CY - Laxenburg SN - 9798331505158 T3 - International Conference on Network and Service Management, ISSN 2165-9605 PY - 2024 PG - 3 DO - 10.23919/CNSM62983.2024.10814304 UR - https://m2.mtmt.hu/api/publication/35760140 ID - 35760140 N1 - Export Date: 14 February 2025; Cited By: 0; Correspondence Address: P. Orosz; Budapest University of Technology and Economics, Dept. of Telecommunications and Artificial Intelligence, Budapest, Hungary; email: orosz@tmit.bme.hu; Conference name: 20th International Conference on Network and Service Management, CNSM 2024; Conference date: 28 October 2024 through 31 October 2024; Conference code: 205683 AB - Our paper addresses the challenges of assessing network neutrality in the context of modern cloud-based services. It highlights the growing complexity for Internet service providers (ISPs) in managing network resources, which may conflict with the traditional best-effort Internet model, potentially compromising network neutrality principles. The authors propose a novel proof-of-concept system that utilizes digital twins to measure and analyze application-specific network neutrality in real-time on the public Internet. This system is designed to be horizontally scalable, adaptable to changing networks, and capable of producing low false rates in neutrality assessments. We detail the architecture of the measurement system, which includes a real client, a measurement server, and the client's digital twin, all of which work together to monitor and compare service quality. The proposed system aims to offer a reliable, real-time method for assessing network neutrality, specifically in terms of how ISPs manage traffic for different applications. © 2024 IFIP. LA - English DB - MTMT ER - TY - JOUR AU - Orosz, Péter AU - Skopkó, Tamás AU - Marosits, Tamás TI - Application-Aware Analysis of Network Neutrality: A Scalable Real-Time Method JF - INFOCOMMUNICATIONS JOURNAL J2 - INFOCOMM J VL - 15 PY - 2023 IS - 1 SP - 77 EP - 86 PG - 10 SN - 2061-2079 DO - 10.36244/ICJ.2023.1.8 UR - https://m2.mtmt.hu/api/publication/33779419 ID - 33779419 N1 - Export Date: 1 June 2023 AB - Internet access subscribers expect a satisfying quality of experience for any accessed service, independently from time, place, and service- and content-type. Besides the everincreasing amount of Internet data, the spectrum of video service platforms offering sharing and streaming also got significantly more comprehensive. Internet access providers try to avoid the exhaustion of network bandwidth by investing in network capacity or setting up higher-level resource management within their infrastructure. The primary question in this domain is how resource management constrains the subscriber to access an arbitrary service and experience good service quality.This question directly relates to network neutrality fundamentals. This paper presents a real-time full-reference objective method to assess network neutrality. It contributes three novelties to support user-centric analysis of potential restraints affecting Internet access quality: i) the proposal supports application-specific measurements and involves real content and real traffic, ii) the measured traffic originates from the content provider’s cloud infrastructure, iii) reference is created in real time. Accordingly, the proposal introduces a novel measurement layout. The key component is the emulated client that provides the real-time reference by emulating the access properties of the real client and accessing the same content simultaneously. We demonstrate the method’s feasibility with an applicationaware proof-of-concept use case: video streaming from a public VoD provider. We have validated the method against the emulated network parameters using an extensive series of laboratory measurements. LA - English DB - MTMT ER - TY - JOUR AU - Orosz, Péter AU - Nagy, Balázs AU - Varga, Pál TI - Detection strategies for post-pandemic DDoS profiles JF - INFOCOMMUNICATIONS JOURNAL J2 - INFOCOMM J VL - 15 PY - 2023 IS - 4 SP - 26 EP - 39 PG - 14 SN - 2061-2079 DO - 10.36244/ICJ.2023.4.4 UR - https://m2.mtmt.hu/api/publication/34547562 ID - 34547562 N1 - Export Date: 8 March 2024 Funding text 1: The research has been partially funded by the Hungarian government’s National Security Cooperative PhD program. AB - The global pandemic lockdowns fostered the digital transition of companies worldwide since most of their employees worked from home using public or private cloud services. Accordingly, these services became the primary targets of the latest generation DDoS threats. While some features of current DDoS attack profiles appeared before the pandemic period, they became significant and reached their current complexity in the recent period. Besides applying novel methods and tools, the attacks’ frequency, extent, and complexity also increased significantly. The combination of various attack vectors opened the way for multi-vector attacks incorporating a unique blend of L3-L7 attacking profiles. Unifying the hit-and-run method and the multi-vector approach contributed to the remarkable rise in success rate. The current paper has two focal points. First, it discusses the profiles of the latest DDoS attacks discovered in real data center infrastructures. To demonstrate and emphasize the changes in attack profile, we reference attack samples recently collected in various data center networks. Second, it provides a comprehensive survey of the state-of-the-art detection methods related to recent attacks. The paper especially focuses on the accuracy and speed of these, mostly networking-related detection approaches. Furthermore, we define features and quantitative and qualitative requirements to support detection methods handling the latest threat profiles. LA - English DB - MTMT ER - TY - JOUR AU - Orosz, Péter AU - Tóthfalusi, Tamás TI - A New Application-Aware No-Reference Quality Assessment Method for IP Voice Services JF - JOURNAL OF NETWORK AND SYSTEMS MANAGEMENT J2 - J NETW SYST MANAG VL - 29 PY - 2021 IS - 3 SN - 1064-7570 DO - 10.1007/s10922-021-09595-8 UR - https://m2.mtmt.hu/api/publication/31958142 ID - 31958142 LA - English DB - MTMT ER - TY - CHAP AU - Orosz, Péter AU - Tóthfalusi, Tamás ED - IEEE, null TI - VoicePerf: A Quality Estimation Approach for No-reference IP Voice Traffic T2 - NOMS 2020 - 2020 IEEE/IFIP Network Operations and Management Symposium: Management in the Age of Softwarization and Artificial Intelligence PB - Institute of Electrical and Electronics Engineers (IEEE) CY - Piscataway (NJ) SN - 9781728149738 T3 - IEEE IFIP Network Operations and Management Symposium, ISSN 1542-1201 PY - 2020 SP - 1 EP - 9 PG - 9 DO - 10.1109/NOMS47738.2020.9110264 UR - https://m2.mtmt.hu/api/publication/31958166 ID - 31958166 LA - English DB - MTMT ER - TY - JOUR AU - Orosz, Péter AU - Tóthfalusi, Tamás AU - Varga, Pál TI - FPGA-Assisted DPI Systems: 100 Gbit/s and Beyond JF - IEEE COMMUNICATIONS SURVEYS AND TUTORIALS J2 - IEEE COMMUN SURV TUTOR VL - 21 PY - 2019 IS - 2 SP - 2015 EP - 2040 PG - 26 SN - 1553-877X DO - 10.1109/COMST.2018.2876196 UR - https://m2.mtmt.hu/api/publication/3419995 ID - 3419995 N1 - Cited By :4 Export Date: 7 December 2020 Correspondence Address: Orosz, P.; Department of Telecommunications and Media Informatics, Budapest University of Technology and EconomicsHungary; email: orosz.peter@tmit.bme.hu Cited By :5 Export Date: 19 April 2021 Correspondence Address: Orosz, P.; Department of Telecommunications and Media Informatics, Hungary; email: orosz.peter@tmit.bme.hu AB - Carrying out deep packet inspection (DPI) in aggregated network connections remains a continuous requirement even though the line rate reaches and exceeds 100 Gb/s. The increasing packet-arrival rate necessitates efficient solutions for on-the-fly packet parsing, packet classification, and distribution for parallelized, software-based payload inspection. Inspection complexity and real-time processing are competing requirements. The deep analysis capabilities of software-based approaches can be enhanced by hardware-based support on time-critical packet parsing and classification. Moreover, some payload inspection tasks can be carried out in hardware as well, further reducing the resources spent on software-based solutions. This paper aims at presenting the state-of-the-art and describing a set of best practices in field programmable gate arrays (FPGA)based packet processing, which can be applied fir DPI-related tasks at 100 Gb/s and beyond. Accordingly, we provide an architectural view of the DPI systems throughout the paper. Besides summarizing the limitations of hardware- and software-based solutions for the three processing phases within a DPI system (packet parsing, packet classification, and payload inspection), this paper reveals the possible trade-offs for choosing the different technical approaches. These limitations include operating frequency, bus size, available memory, on-chip physical resources for hardware-based implementations, and CPU time for software-based solutions. LA - English DB - MTMT ER - TY - CHAP AU - Orosz, Péter AU - Varga, Pál AU - Soós, Gábor AU - Hegedűs, Csaba Miklós TI - QoS Guarantees for Industrial IoT Applications over LTE - a Feasibility Study T2 - 2019 IEEE International Conference on Industrial Cyber Physical Systems, ICPS 2019 PB - Institute of Electrical and Electronics Engineers (IEEE) CY - Piscataway (NJ) SN - 9781538685006 PY - 2019 SP - 667 EP - 672 PG - 6 DO - 10.1109/ICPHYS.2019.8780308 UR - https://m2.mtmt.hu/api/publication/31666897 ID - 31666897 N1 - Funding Agency and Grant Number: EU ARTEMIS JU funding [737459]; BME Artificial Intelligence FIKP grant of EMMI (BME FIKP-MI/SC) Funding text: This work is supported by the EU ARTEMIS JU funding, under grant agreement 737459 (project Productive4.0). Part of the research reported in this paper was supported by the BME Artificial Intelligence FIKP grant of EMMI (BME FIKP-MI/SC). IEEE Industrial Electronics Society (IES); The Institute of Electrical and Electronics Engineers (IEEE) Dept. of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary Telecommunication Division, AITIA International Inc, Budapest, Hungary Conference code: 150221 Cited By :5 Export Date: 6 December 2020 Funding details: BME FIKP-MI/SC Funding details: Productive4.0, 737459 Funding text 1: ACKNOWLEDGMENT This work is supported by the EU ARTEMIS JU funding, under grant agreement 737459 (project Productive4.0). Part of the research reported in this paper was supported by the BME Artificial Intelligence FIKP grant of EMMI (BME FIKP-MI/SC). IEEE Industrial Electronics Society (IES); The Institute of Electrical and Electronics Engineers (IEEE) Dept. of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary Telecommunication Division, AITIA International Inc, Budapest, Hungary Conference code: 150221 Cited By :5 Export Date: 7 December 2020 Funding details: BME FIKP-MI/SC Funding details: Productive4.0, 737459 Funding text 1: ACKNOWLEDGMENT This work is supported by the EU ARTEMIS JU funding, under grant agreement 737459 (project Productive4.0). Part of the research reported in this paper was supported by the BME Artificial Intelligence FIKP grant of EMMI (BME FIKP-MI/SC). AB - Industrial automation systems traditionally require communication systems to have high availability, high security and low latency. This results in efficient protocols with low protocol-processing overhead, but somewhat rigid communication systems that are cumbersome to scale up when deployed. On the other hand, Internet Protocol based communication which is often preferred by IoT systems - offer high flexibility, but best-effort reliability. Furthermore, various radio access technologies have been created for IoT devices facilitating their IP networking as well. Nevertheless, these wireless technologies are rarely capable of corresponding to the strict requirements of complex industrial use cases, they usually cannot certain the necessary Quality of Service (QoS) promises.On the contrary, 5G mobile technologies are being developed exactly for such industrial and automation IoT use cases. Certainly, there are traffic prioritization techniques available for 4G and 5G systems, but their capabilities need to be investigated for Industrial IoT feasibility, before deployment. This paper aims to provide a feasibility study for applying mobile networking technologies (4G and 5G) - and its QoS guarantees - to IIoT applications. The proposed methodology can be extended for benchmarking whether a given use case can benefit from applying mobile networking for its various industrial and automation systems. LA - English DB - MTMT ER - TY - JOUR AU - Orosz, Péter AU - Kulik, Ivett AU - Marosits, Tamás TI - Internet-hozzáférések teljesítményvizsgálata webböngészőben JF - HÍRADÁSTECHNIKA (1962) J2 - HÍRADÁSTECHNIKA VL - LXXIII. PY - 2018 IS - 1 SP - 37 EP - 44 PG - 8 SN - 0018-2028 UR - https://m2.mtmt.hu/api/publication/3421067 ID - 3421067 N1 - # Cím ismeretlen LA - Hungarian DB - MTMT ER - TY - CHAP AU - Nagy, Balázs AU - Orosz, Péter AU - Tóthfalusi, Tamás AU - László, Kovács AU - Varga, Pál ED - IEEE, , TI - Detecting DDoS Attacks within Milliseconds by Using FPGA-based Hardware Acceleration T2 - IEEE/IFIP Network Operations and Management Symposium: Cognitive Management in a Cyber World, NOMS 2018 PB - Institute of Electrical and Electronics Engineers (IEEE) CY - Piscataway (NJ) SN - 9781538634158 PY - 2018 PG - 4 DO - 10.1109/NOMS.2018.8406299 UR - https://m2.mtmt.hu/api/publication/3421153 ID - 3421153 N1 - AITIA International Inc., Telecommunications Division, Budapest, Hungary Budapest University of Technology and Economics, Dept. of Telecommunication and Media Informatics, Budapest, Hungary Conference code: 137784 Cited By :5 Export Date: 6 December 2020 AITIA International Inc., Telecommunications Division, Budapest, Hungary Budapest University of Technology and Economics, Dept. of Telecommunication and Media Informatics, Budapest, Hungary Conference code: 137784 Cited By :5 Export Date: 7 December 2020 LA - English DB - MTMT ER -