Pub Date : 2022-07-18DOI: 10.1109/MN55117.2022.9887664
L. Schenato, Nicola Fabbian, G. D. Santa, P. Simonini, F. D. Polo, Giacomo Tedesco, G. Marcato, S. Cola
In this work, we present the application of optical fiber sensors to monitor and characterize the soil temperature of river embankments. The soil temperature represents an indicator of possible seepage flows that may hamper the stability of the structure and can be used to characterize the hydraulic behavior of the embankment. Optical fiber sensors represent, to date, the only viable technology capable of measuring the temperature with the required spatial resolution in this kind of application.
{"title":"Distributed optical fiber sensors for the soil temperature measurement in river embankments","authors":"L. Schenato, Nicola Fabbian, G. D. Santa, P. Simonini, F. D. Polo, Giacomo Tedesco, G. Marcato, S. Cola","doi":"10.1109/MN55117.2022.9887664","DOIUrl":"https://doi.org/10.1109/MN55117.2022.9887664","url":null,"abstract":"In this work, we present the application of optical fiber sensors to monitor and characterize the soil temperature of river embankments. The soil temperature represents an indicator of possible seepage flows that may hamper the stability of the structure and can be used to characterize the hydraulic behavior of the embankment. Optical fiber sensors represent, to date, the only viable technology capable of measuring the temperature with the required spatial resolution in this kind of application.","PeriodicalId":148281,"journal":{"name":"2022 IEEE International Symposium on Measurements & Networking (M&N)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121049331","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}
Pub Date : 2022-07-18DOI: 10.1109/MN55117.2022.9887643
Alessandro Brighente, M. Conti, Gulshan Kumar, Reza Ghanbari, R. Saha
Distributed Ledger Technology (DLT) is one of the most promising technology at present with applications in different domains, such as Cyber-Physical Systems (CPS) and Internet of Thing (IoT). IOTA is an example of Directed Acyclic Graph (DAG)-based DLTs applicable to IoT, addressing the issues of scalability, consensus complexity, and mining incentives of blockchains. In order to join the network and to later disseminate fresh information, nodes exploit IOTA's autopeering module. The security of this module is hence of fundamental importance for the network liveness, however this requirement has never been analyzed in the literature. In this paper, we provide the first security analysis of the autopeering module of the Coordicide, IOTA's main framework. We divide the contribution in two parts: i) we show that the peer-discovery process in the autopeering module is vulnerable to flooding attack, a type of Denial of Service (DoS), and ii) we propose Time Constrained Identity Match (TID), a novel protocol to mitigate the flooding attack. In particular, we compare two implementations of TID: leaky-TID based on leaky bucket, and token-Tid based on token bucket. We discuss their suitability to IOTA both in terms of effectiveness in mitigating the flooding attack and in terms of resource consumption (memory and CPU). Based on the results, we observe that leaky-TID shows the better performance in preventing flooding attacks, reducing the traffic under attack by 67% and reducing memory consumption by 12.5%.
{"title":"Stopping Floods with Buckets: Attack and Countermeasure for IOTA Autopeering","authors":"Alessandro Brighente, M. Conti, Gulshan Kumar, Reza Ghanbari, R. Saha","doi":"10.1109/MN55117.2022.9887643","DOIUrl":"https://doi.org/10.1109/MN55117.2022.9887643","url":null,"abstract":"Distributed Ledger Technology (DLT) is one of the most promising technology at present with applications in different domains, such as Cyber-Physical Systems (CPS) and Internet of Thing (IoT). IOTA is an example of Directed Acyclic Graph (DAG)-based DLTs applicable to IoT, addressing the issues of scalability, consensus complexity, and mining incentives of blockchains. In order to join the network and to later disseminate fresh information, nodes exploit IOTA's autopeering module. The security of this module is hence of fundamental importance for the network liveness, however this requirement has never been analyzed in the literature. In this paper, we provide the first security analysis of the autopeering module of the Coordicide, IOTA's main framework. We divide the contribution in two parts: i) we show that the peer-discovery process in the autopeering module is vulnerable to flooding attack, a type of Denial of Service (DoS), and ii) we propose Time Constrained Identity Match (TID), a novel protocol to mitigate the flooding attack. In particular, we compare two implementations of TID: leaky-TID based on leaky bucket, and token-Tid based on token bucket. We discuss their suitability to IOTA both in terms of effectiveness in mitigating the flooding attack and in terms of resource consumption (memory and CPU). Based on the results, we observe that leaky-TID shows the better performance in preventing flooding attacks, reducing the traffic under attack by 67% and reducing memory consumption by 12.5%.","PeriodicalId":148281,"journal":{"name":"2022 IEEE International Symposium on Measurements & Networking (M&N)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130646738","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}
Pub Date : 2022-07-18DOI: 10.1109/MN55117.2022.9887767
P. Ferrari, P. Bellagente, A. Depari, D. F. Carvalho, A. Flammini, M. Pasetti, S. Rinaldi, E. Sisinni
The LoRa-REP is transparent enhancement of LoRa W Anthat can effectively handle emergency transmissions caused by important, but sporadic, events. LoRa-REP is designed to shorten the average latency and reduce emergency communication failure probability using a message replication approach, suitable for Internet-of- Things (loT) applications. A hardware implementation and a proof-of-concept scenario are realized, together with a simulator. Previous experiments demonstrate feasibility, while scalability is shown being somehow limited especially if short transaction delay are needed. For this reason, this work proposes a comparative analysis of the pre-existing LoRa-REP scalability and, for the first time, customizes standards slotted delay strategies to the specific LoRA-REP scenarios. The simulation considers up to 10 co-located LoRa-REP nodes and as much as 1000 standard LoRa W Annodes. The results show that the proposed LoRa-REP with slotted delay can scale, maintain compatibility with standard LoRa Wanbackend and, at the same time, optimize average performance (up to 10%). Moreover, the simulations can be used to obtain the set of parameters of LoRa-REP with slotted delay that match goals of each application.
LoRa- rep是LoRa W - an的透明增强，可以有效地处理由重要但零星的事件引起的紧急传输。LoRa-REP旨在利用消息复制方法缩短平均延迟并降低紧急通信失败概率，适用于物联网(loT)应用。实现了硬件实现和概念验证场景，以及模拟器。先前的实验证明了可行性，但可扩展性在一定程度上受到限制，特别是在需要短事务延迟的情况下。出于这个原因，本研究提出了对现有的LoRa-REP可扩展性的比较分析，并首次针对特定的LoRa-REP场景定制了标准槽延迟策略。该模拟考虑多达10个共存的LoRa- rep节点和多达1000个标准LoRa W节点。结果表明，提出的带槽延迟的LoRa- rep可以扩展，保持与标准LoRa Wanbackend的兼容性，同时优化平均性能(高达10%)。此外，通过仿真可以得到符合各应用目标的有槽延迟的LoRa-REP参数集。
{"title":"Improving LoRa-REP scalability in emergency scenarios by means of slotted delay","authors":"P. Ferrari, P. Bellagente, A. Depari, D. F. Carvalho, A. Flammini, M. Pasetti, S. Rinaldi, E. Sisinni","doi":"10.1109/MN55117.2022.9887767","DOIUrl":"https://doi.org/10.1109/MN55117.2022.9887767","url":null,"abstract":"The LoRa-REP is transparent enhancement of LoRa W Anthat can effectively handle emergency transmissions caused by important, but sporadic, events. LoRa-REP is designed to shorten the average latency and reduce emergency communication failure probability using a message replication approach, suitable for Internet-of- Things (loT) applications. A hardware implementation and a proof-of-concept scenario are realized, together with a simulator. Previous experiments demonstrate feasibility, while scalability is shown being somehow limited especially if short transaction delay are needed. For this reason, this work proposes a comparative analysis of the pre-existing LoRa-REP scalability and, for the first time, customizes standards slotted delay strategies to the specific LoRA-REP scenarios. The simulation considers up to 10 co-located LoRa-REP nodes and as much as 1000 standard LoRa W Annodes. The results show that the proposed LoRa-REP with slotted delay can scale, maintain compatibility with standard LoRa Wanbackend and, at the same time, optimize average performance (up to 10%). Moreover, the simulations can be used to obtain the set of parameters of LoRa-REP with slotted delay that match goals of each application.","PeriodicalId":148281,"journal":{"name":"2022 IEEE International Symposium on Measurements & Networking (M&N)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121687519","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}
Pub Date : 2022-07-18DOI: 10.1109/MN55117.2022.9887721
Paolo Caruso, Domenico Di Caro, S. D. Iacono, V. Paciello
In recent years, a growing necessity of monitoring facilities like gas or water pipelines has raised to ensure high security and proper maintenance of the infrastructures. In particular, in piping systems, there is the need to monitor the cathodic protection voltage, whose presence allows to protect the pipeline from corrosive effects and avoid damage to the system. The state of protection of the pipes also needs to be communicated outside of the measurement point. Unfortunately, most pipelines are located in places where creating a wireless communication network is very expensive. An innovative and unconventional way to achieve this goal is to use the pipelines as a communication channel, avoiding installing dedicated data communication systems. Starting from the authors' background, in this paper, an opamp-based circuit is presented and adopted for the information transfer over gas pipelines. A characterization of the presented circuit is made to find the relationship between the reflection coefficient and the impedance connected to a specific port of the circulator. Measured the pipeline input impedance and knowing the theory about the transmission lines, the output impedance of the circulator is adjusted to obtain the impedance matching with the line to have a complete transmission of the signal on the gas pipeline. In the last section of the paper, the effective improvement of the communication channel obtained by inserting the circulator in the communication link is shown. The final aim is to transmit a certain number of bytes with a private communication protocol, in order to avoid informatic attacks and to improve the cyber-security level.
{"title":"Impedance Adaptation Technique to Improve Pipeline Communication Distance","authors":"Paolo Caruso, Domenico Di Caro, S. D. Iacono, V. Paciello","doi":"10.1109/MN55117.2022.9887721","DOIUrl":"https://doi.org/10.1109/MN55117.2022.9887721","url":null,"abstract":"In recent years, a growing necessity of monitoring facilities like gas or water pipelines has raised to ensure high security and proper maintenance of the infrastructures. In particular, in piping systems, there is the need to monitor the cathodic protection voltage, whose presence allows to protect the pipeline from corrosive effects and avoid damage to the system. The state of protection of the pipes also needs to be communicated outside of the measurement point. Unfortunately, most pipelines are located in places where creating a wireless communication network is very expensive. An innovative and unconventional way to achieve this goal is to use the pipelines as a communication channel, avoiding installing dedicated data communication systems. Starting from the authors' background, in this paper, an opamp-based circuit is presented and adopted for the information transfer over gas pipelines. A characterization of the presented circuit is made to find the relationship between the reflection coefficient and the impedance connected to a specific port of the circulator. Measured the pipeline input impedance and knowing the theory about the transmission lines, the output impedance of the circulator is adjusted to obtain the impedance matching with the line to have a complete transmission of the signal on the gas pipeline. In the last section of the paper, the effective improvement of the communication channel obtained by inserting the circulator in the communication link is shown. The final aim is to transmit a certain number of bytes with a private communication protocol, in order to avoid informatic attacks and to improve the cyber-security level.","PeriodicalId":148281,"journal":{"name":"2022 IEEE International Symposium on Measurements & Networking (M&N)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126455657","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}
Pub Date : 2022-07-18DOI: 10.1109/MN55117.2022.9887739
J. Pereira, A. Espírito-Santo
IEEE 1451 standard has the properties required by smart transducers networks as defined by the cyber-physical System, Industrial Internet of Things and Industry 4.0 concepts. The open-access online platform designs and validates IEEE 1451 compliant transducers. Users can create, edit, and manage Transducer Electronic Data Sheets stored in a database. The solution presented generates automatically project templates for low-power microcontrollers MSP430. The transducer is evaluated and tested, observing the packages of messages exchanged between the Transducer Interface Module and the Network-Capable Application Processor.
{"title":"Open Access Online Platform for Transducers Development Conforming the IEEE 1451","authors":"J. Pereira, A. Espírito-Santo","doi":"10.1109/MN55117.2022.9887739","DOIUrl":"https://doi.org/10.1109/MN55117.2022.9887739","url":null,"abstract":"IEEE 1451 standard has the properties required by smart transducers networks as defined by the cyber-physical System, Industrial Internet of Things and Industry 4.0 concepts. The open-access online platform designs and validates IEEE 1451 compliant transducers. Users can create, edit, and manage Transducer Electronic Data Sheets stored in a database. The solution presented generates automatically project templates for low-power microcontrollers MSP430. The transducer is evaluated and tested, observing the packages of messages exchanged between the Transducer Interface Module and the Network-Capable Application Processor.","PeriodicalId":148281,"journal":{"name":"2022 IEEE International Symposium on Measurements & Networking (M&N)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122298803","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}
Pub Date : 2022-07-18DOI: 10.1109/MN55117.2022.9887768
L. Ferrigno, F. Milano, Valentina Pingerna, G. Cerro, M. Laracca
The localization task in sensor networks is partic-ularly critical whenever the sensor measurements are position-related, as in case of thermal and electromagnetic quantities. The deployment of a sensor network often requires the usage of low-cost devices able to achieve acceptable measurement accuracy and having the need to retrieve fast and accurate positioning information. In such networks, the localization task is generally performed by a special node coordinating the network. Nevertheless, its computing power is often limited. To this aim, in this paper we compare two different positioning techniques (least square minimization, grid search), to be applied in Ultra- Wide-Band positioning scheme, from the accuracy point of view and computing time required for accomplishing the task. They differ in working principle, needed a priori information, localization resolution and time to completion parameter. According to the available resources, the adoption of one of them should be prefer-able to the other one. Obtained results prove the goodness of both methods, specifically ranking them by application purposes. The paper is intended to give the designers an extensive analysis to evaluate pros and cons to adopt a completely blind positioning technique, namely the least square minimization, versus a more informed and constrained system, as the grid search case.
{"title":"Performance comparison in Ultra Wide Band positioning in sensor networks: least square minimization versus grid search approach","authors":"L. Ferrigno, F. Milano, Valentina Pingerna, G. Cerro, M. Laracca","doi":"10.1109/MN55117.2022.9887768","DOIUrl":"https://doi.org/10.1109/MN55117.2022.9887768","url":null,"abstract":"The localization task in sensor networks is partic-ularly critical whenever the sensor measurements are position-related, as in case of thermal and electromagnetic quantities. The deployment of a sensor network often requires the usage of low-cost devices able to achieve acceptable measurement accuracy and having the need to retrieve fast and accurate positioning information. In such networks, the localization task is generally performed by a special node coordinating the network. Nevertheless, its computing power is often limited. To this aim, in this paper we compare two different positioning techniques (least square minimization, grid search), to be applied in Ultra- Wide-Band positioning scheme, from the accuracy point of view and computing time required for accomplishing the task. They differ in working principle, needed a priori information, localization resolution and time to completion parameter. According to the available resources, the adoption of one of them should be prefer-able to the other one. Obtained results prove the goodness of both methods, specifically ranking them by application purposes. The paper is intended to give the designers an extensive analysis to evaluate pros and cons to adopt a completely blind positioning technique, namely the least square minimization, versus a more informed and constrained system, as the grid search case.","PeriodicalId":148281,"journal":{"name":"2022 IEEE International Symposium on Measurements & Networking (M&N)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132145082","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}
Pub Date : 2022-07-18DOI: 10.1109/MN55117.2022.9887744
Luis Garcia, G. Bartlett, Srivatsan Ravi, Harun Ibrahim, W. Hardaker, Erik Kline
Machine learning is increasingly applied to network traffic analysis to aid in tasks such as quality of service management, trend monitoring, and security. Recent advances in deep learning have enabled not only the classification of encrypted transits, but classification on a per-packet level. End-to-end deep learning models are becoming increasingly ubiq-uitous given their ease of use, i.e., developers do not need to engineer features, and their apparent versatility. However, deep learning entails black-box models that hinder the capability to debug and explain classifications. Moreover, the computational complexity of deep learning can incur unnecessary latency, which is problematic for real-time classification needs. In this paper, we propose a methodology to interpret black-box, deep learning-based encrypted network traffic classification models, with an attempt to understand the dominant features a classifier is focusing on for a given task. We evaluate our approach on state-of-the-art deep learning classification techniques for encrypted per-packet classification and demonstrate how interpretability can be used to debug and improve the training pipeline while significantly reducing the size of the deep learning model. We propose future directions toward optimizing model performance while maintaining explainability.
{"title":"Explaining Deep Learning Models for Per-packet Encrypted Network Traffic Classification","authors":"Luis Garcia, G. Bartlett, Srivatsan Ravi, Harun Ibrahim, W. Hardaker, Erik Kline","doi":"10.1109/MN55117.2022.9887744","DOIUrl":"https://doi.org/10.1109/MN55117.2022.9887744","url":null,"abstract":"Machine learning is increasingly applied to network traffic analysis to aid in tasks such as quality of service management, trend monitoring, and security. Recent advances in deep learning have enabled not only the classification of encrypted transits, but classification on a per-packet level. End-to-end deep learning models are becoming increasingly ubiq-uitous given their ease of use, i.e., developers do not need to engineer features, and their apparent versatility. However, deep learning entails black-box models that hinder the capability to debug and explain classifications. Moreover, the computational complexity of deep learning can incur unnecessary latency, which is problematic for real-time classification needs. In this paper, we propose a methodology to interpret black-box, deep learning-based encrypted network traffic classification models, with an attempt to understand the dominant features a classifier is focusing on for a given task. We evaluate our approach on state-of-the-art deep learning classification techniques for encrypted per-packet classification and demonstrate how interpretability can be used to debug and improve the training pipeline while significantly reducing the size of the deep learning model. We propose future directions toward optimizing model performance while maintaining explainability.","PeriodicalId":148281,"journal":{"name":"2022 IEEE International Symposium on Measurements & Networking (M&N)","volume":"225 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132350968","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}
Pub Date : 2022-07-18DOI: 10.1109/MN55117.2022.9887741
G. Giorgi, A. Pozzebon, C. Narduzzi
LoRaWAN is well suited for the transmission of small amounts of numeric data, while its technical features are not conceived for the continuous real-time monitoring of time-evolving signals. The aim of this paper is to discuss the usability of the Long Range Wide Area Network (LoRaWAN) technology for the continuous transmission of signals characterized by different scales of variability. At the purpose the so-called burst-mode acquisition is considered and analyzed for a LoraWAN infrastructure. Furthermore, a very simple messaging protocol is introduced to increase data throughput, by allowing application-level messages to be sent using the same data message, avoiding extra overload. To demonstrate this approach, the paper focuses on possible techniques to perform a long-term monitoring of the electrocardiographic (ECG) signal over a LoRaWAN communication infrastructure where duty cycle induced constraints are carefully considered. The analysis of real signals proves the feasibility of the proposed system, which can be easily generalized for other kind of signals.
{"title":"Waveform monitoring with LoRaWAN: Is it feasible?","authors":"G. Giorgi, A. Pozzebon, C. Narduzzi","doi":"10.1109/MN55117.2022.9887741","DOIUrl":"https://doi.org/10.1109/MN55117.2022.9887741","url":null,"abstract":"LoRaWAN is well suited for the transmission of small amounts of numeric data, while its technical features are not conceived for the continuous real-time monitoring of time-evolving signals. The aim of this paper is to discuss the usability of the Long Range Wide Area Network (LoRaWAN) technology for the continuous transmission of signals characterized by different scales of variability. At the purpose the so-called burst-mode acquisition is considered and analyzed for a LoraWAN infrastructure. Furthermore, a very simple messaging protocol is introduced to increase data throughput, by allowing application-level messages to be sent using the same data message, avoiding extra overload. To demonstrate this approach, the paper focuses on possible techniques to perform a long-term monitoring of the electrocardiographic (ECG) signal over a LoRaWAN communication infrastructure where duty cycle induced constraints are carefully considered. The analysis of real signals proves the feasibility of the proposed system, which can be easily generalized for other kind of signals.","PeriodicalId":148281,"journal":{"name":"2022 IEEE International Symposium on Measurements & Networking (M&N)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124632501","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}
Pub Date : 2022-07-18DOI: 10.1109/MN55117.2022.9887775
Idio Guarino, Giampaolo Bovenzi, Davide Di Monda, Giuseppe Aceto, D. Ciuonzo, A. Pescapé
Current intrusion detection techniques cannot keep up with the increasing amount and complexity of cyber attacks. In fact, most of the traffic is encrypted and does not allow to apply deep packet inspection approaches. In recent years, Machine Learning techniques have been proposed for post-mortem detection of network attacks, and many datasets have been shared by research groups and organizations for training and validation. Differently from the vast related literature, in this paper we propose an early classification approach conducted on CSE-CIC-IDS2018 dataset, which contains both benign and malicious traffic, for the detection of malicious attacks before they could damage an organization. To this aim, we investigated a different set of features, and the sensitivity of performance of five classification algorithms to the number of observed packets. Results show that ML approaches relying on ten packets provide satisfactory results.
{"title":"On the use of Machine Learning Approaches for the Early Classification in Network Intrusion Detection","authors":"Idio Guarino, Giampaolo Bovenzi, Davide Di Monda, Giuseppe Aceto, D. Ciuonzo, A. Pescapé","doi":"10.1109/MN55117.2022.9887775","DOIUrl":"https://doi.org/10.1109/MN55117.2022.9887775","url":null,"abstract":"Current intrusion detection techniques cannot keep up with the increasing amount and complexity of cyber attacks. In fact, most of the traffic is encrypted and does not allow to apply deep packet inspection approaches. In recent years, Machine Learning techniques have been proposed for post-mortem detection of network attacks, and many datasets have been shared by research groups and organizations for training and validation. Differently from the vast related literature, in this paper we propose an early classification approach conducted on CSE-CIC-IDS2018 dataset, which contains both benign and malicious traffic, for the detection of malicious attacks before they could damage an organization. To this aim, we investigated a different set of features, and the sensitivity of performance of five classification algorithms to the number of observed packets. Results show that ML approaches relying on ten packets provide satisfactory results.","PeriodicalId":148281,"journal":{"name":"2022 IEEE International Symposium on Measurements & Networking (M&N)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125065872","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}
Pub Date : 2022-07-18DOI: 10.1109/MN55117.2022.9887676
N. Djuric, D. Kljajić, Teodora Gavrilov, Nadja Markovic Golubovic, S. Djuric
The man-made electromagnetic field (EMF) has been extensively used in last several decades, particularly since wireless telecommunication technology experienced substantial expansion. Simultaneously, the exposure to EMF has become an issue and inevitable part of intensive public debate on health ef-fects. Thus, the International Commission for Non-Ionizing Ra-diation Protection (ICNIRP) has published ICNIRP 2020 guide-lines, in order to ensure high-quality protection against all so far acknowledged health risks when population is/can be exposed to EMFs. Beside the latest updates of the exposure limits, which are based on improved scientific accuracy in most recent scien-tific studies, an important task of the ICNIRP 2020 is also a rec-ommendation to national decision-makers to update their EMF legislation. Such accomplishment is fundamental for their activ-ities on EMF investigation, since all activities should be lined up with up-to-date recommendations. In this paper, the standardi-zation update of the most important Serbian EMF legislation acts is considered, highlighting parts of prescribed EMF expo-sure limits that should be altered in the near future.
{"title":"The ICNIRP 2020 Guidelines and Standardization update of Serbian EMF radiation exposure limits","authors":"N. Djuric, D. Kljajić, Teodora Gavrilov, Nadja Markovic Golubovic, S. Djuric","doi":"10.1109/MN55117.2022.9887676","DOIUrl":"https://doi.org/10.1109/MN55117.2022.9887676","url":null,"abstract":"The man-made electromagnetic field (EMF) has been extensively used in last several decades, particularly since wireless telecommunication technology experienced substantial expansion. Simultaneously, the exposure to EMF has become an issue and inevitable part of intensive public debate on health ef-fects. Thus, the International Commission for Non-Ionizing Ra-diation Protection (ICNIRP) has published ICNIRP 2020 guide-lines, in order to ensure high-quality protection against all so far acknowledged health risks when population is/can be exposed to EMFs. Beside the latest updates of the exposure limits, which are based on improved scientific accuracy in most recent scien-tific studies, an important task of the ICNIRP 2020 is also a rec-ommendation to national decision-makers to update their EMF legislation. Such accomplishment is fundamental for their activ-ities on EMF investigation, since all activities should be lined up with up-to-date recommendations. In this paper, the standardi-zation update of the most important Serbian EMF legislation acts is considered, highlighting parts of prescribed EMF expo-sure limits that should be altered in the near future.","PeriodicalId":148281,"journal":{"name":"2022 IEEE International Symposium on Measurements & Networking (M&N)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128821101","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：