Pub Date : 2022-11-30DOI: 10.1109/LATINCOM56090.2022.10000477
André L. B. Molina, Vinícius P. Gonçalves, Rafael Timóteo de Sousa, Marcel Pividal, R. Meneguette, G. P. R. Filho
In recent years, user behavior anomaly detection has been gaining attention in cybersecurity. A crucial challenge that has been discussed in the literature is that supervised models that use vast amounts of data for training do not apply to real scenarios for anomaly detection. Within this context, the requirement to gather datasets with labeled behavior anomalies has proven to be a significant limiting factor for evaluating different models. This paper presents WEAPON, an unsupervised learning-based architecture for user behavior anomaly detection that requires a small amount of data for building behavior profiles considering the individuality of each user. WEAPON implements the weak supervision-based behavior anomaly labeling approach using Snorkel. When compared to other approaches, WEAPON proved to be more efficient, surpassing the ROC curve of the second best model by 4.31%. Furthermore, WEAPON outperforms rule-based methods by finding anomalies that an expert would not anticipate.
{"title":"A Lightweight Unsupervised Learning Architecture to Enhance User Behavior Anomaly Detection","authors":"André L. B. Molina, Vinícius P. Gonçalves, Rafael Timóteo de Sousa, Marcel Pividal, R. Meneguette, G. P. R. Filho","doi":"10.1109/LATINCOM56090.2022.10000477","DOIUrl":"https://doi.org/10.1109/LATINCOM56090.2022.10000477","url":null,"abstract":"In recent years, user behavior anomaly detection has been gaining attention in cybersecurity. A crucial challenge that has been discussed in the literature is that supervised models that use vast amounts of data for training do not apply to real scenarios for anomaly detection. Within this context, the requirement to gather datasets with labeled behavior anomalies has proven to be a significant limiting factor for evaluating different models. This paper presents WEAPON, an unsupervised learning-based architecture for user behavior anomaly detection that requires a small amount of data for building behavior profiles considering the individuality of each user. WEAPON implements the weak supervision-based behavior anomaly labeling approach using Snorkel. When compared to other approaches, WEAPON proved to be more efficient, surpassing the ROC curve of the second best model by 4.31%. Furthermore, WEAPON outperforms rule-based methods by finding anomalies that an expert would not anticipate.","PeriodicalId":221354,"journal":{"name":"2022 IEEE Latin-American Conference on Communications (LATINCOM)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122506506","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 : 2022-11-30DOI: 10.1109/LATINCOM56090.2022.10000486
Shalitha Wijethilaka, Madhusanka Liyanage
Fifth Generation (5G) and beyond telecommunication networks introduce a set of novel technologies such as private 5G networks, also known as Local 5G Operator (L5GO), and Network Slicing (NS) for the realization of diverse novel applications with heterogeneous network requirements. Among other network-level requirements, security is a critical challenge in L5GO networks. Facilitating the security requirements in an NS-enabled L5GO environment while increasing resource utilization efficiency is arduous. This paper introduces a novel security framework for NS-enabled L5GO networks. The proposed framework increases the scalability, dynamicity, and flexibility of the system while focusing on reducing the cost. Moreover, this paper verifies the functionality of the security framework using a real testbed. Extensive experiments are performed to analyze the framework’s behaviour in terms of resource conservation, cost reduction, and latency variation.
{"title":"A Novel Network Slicing based Security-as-a-Service (SECaaS) Framework for Private 5G Networks","authors":"Shalitha Wijethilaka, Madhusanka Liyanage","doi":"10.1109/LATINCOM56090.2022.10000486","DOIUrl":"https://doi.org/10.1109/LATINCOM56090.2022.10000486","url":null,"abstract":"Fifth Generation (5G) and beyond telecommunication networks introduce a set of novel technologies such as private 5G networks, also known as Local 5G Operator (L5GO), and Network Slicing (NS) for the realization of diverse novel applications with heterogeneous network requirements. Among other network-level requirements, security is a critical challenge in L5GO networks. Facilitating the security requirements in an NS-enabled L5GO environment while increasing resource utilization efficiency is arduous. This paper introduces a novel security framework for NS-enabled L5GO networks. The proposed framework increases the scalability, dynamicity, and flexibility of the system while focusing on reducing the cost. Moreover, this paper verifies the functionality of the security framework using a real testbed. Extensive experiments are performed to analyze the framework’s behaviour in terms of resource conservation, cost reduction, and latency variation.","PeriodicalId":221354,"journal":{"name":"2022 IEEE Latin-American Conference on Communications (LATINCOM)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124840576","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 : 2022-11-30DOI: 10.1109/LATINCOM56090.2022.10000719
Fábio D. L. Coutinho, Hugerles S. Silva, P. Georgieva, Arnaldo S. R. Oliveira
In this paper, it is proposed a convolutional neural network (CNN)-based algorithm for joint estimation of the channel and phase noise in orthogonal frequency-division multiplexing (OFDM) relay systems. Due to the time-varying nature of the oscillator phase noise in higher frequency bands, this impairment can no longer be treated as additive white gaussian noise leading to the deterioration in the overall performance of wireless communication systems. Thus, jointly with the channel frequency response, the proposed algorithm infers the intercarrier interference in the received baseband signal introduced by the phase noise of the transmitter and receiver oscillators. The impact of the number of cascaded channels between the source and the destination of the relay system is also studied. The proposed CNN-based approach has the potential to deal with the challenging phase noise problem, which is still an open issue for the cascaded channels. The obtained results show that due to the relevant intercarrier interference mitigation, the CNN-based approach outperforms the least square practical estimation and presents a considerable improvement in the bit error rate (BER). To the best of author’s knowledge, this is the first work that unifies the relay cascaded channel and phase noise estimation in the frequency domain using a CNN-based algorithm.
{"title":"CNN-based Algorithm for Joint Channel and Phase Noise Estimation in OFDM Relay Systems","authors":"Fábio D. L. Coutinho, Hugerles S. Silva, P. Georgieva, Arnaldo S. R. Oliveira","doi":"10.1109/LATINCOM56090.2022.10000719","DOIUrl":"https://doi.org/10.1109/LATINCOM56090.2022.10000719","url":null,"abstract":"In this paper, it is proposed a convolutional neural network (CNN)-based algorithm for joint estimation of the channel and phase noise in orthogonal frequency-division multiplexing (OFDM) relay systems. Due to the time-varying nature of the oscillator phase noise in higher frequency bands, this impairment can no longer be treated as additive white gaussian noise leading to the deterioration in the overall performance of wireless communication systems. Thus, jointly with the channel frequency response, the proposed algorithm infers the intercarrier interference in the received baseband signal introduced by the phase noise of the transmitter and receiver oscillators. The impact of the number of cascaded channels between the source and the destination of the relay system is also studied. The proposed CNN-based approach has the potential to deal with the challenging phase noise problem, which is still an open issue for the cascaded channels. The obtained results show that due to the relevant intercarrier interference mitigation, the CNN-based approach outperforms the least square practical estimation and presents a considerable improvement in the bit error rate (BER). To the best of author’s knowledge, this is the first work that unifies the relay cascaded channel and phase noise estimation in the frequency domain using a CNN-based algorithm.","PeriodicalId":221354,"journal":{"name":"2022 IEEE Latin-American Conference on Communications (LATINCOM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128908716","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 : 2022-11-30DOI: 10.1109/LATINCOM56090.2022.10000557
M. Lima, L. Tarelho
TWSTFT is one of the most accurate methods to compare and synchronize time scales between remote stations connected by a geostationary satellite. The high accuracy of the TWSTFT time measurement allows it to be used to locate a geostationary satellite. This results in a lower location uncertainty, which decreases the number of maneuvers made to avoid the debris collision. The Brazilian geostationary satellite (SGDC) and the time and frequency standards laboratories in Latin America could be used to improve the location of the SGDC with the TWSTFT links. The satellite location uncertainty is calculated using a geometry factor called PDOP. The results indicate that there is a way to accentuate the reduction of the PDOP and, consequently, decrease the location uncertainty of the geostationary satellite.
{"title":"Characterization of PDOP for Locating a Geostationary Satellite using TWSTFT Links","authors":"M. Lima, L. Tarelho","doi":"10.1109/LATINCOM56090.2022.10000557","DOIUrl":"https://doi.org/10.1109/LATINCOM56090.2022.10000557","url":null,"abstract":"TWSTFT is one of the most accurate methods to compare and synchronize time scales between remote stations connected by a geostationary satellite. The high accuracy of the TWSTFT time measurement allows it to be used to locate a geostationary satellite. This results in a lower location uncertainty, which decreases the number of maneuvers made to avoid the debris collision. The Brazilian geostationary satellite (SGDC) and the time and frequency standards laboratories in Latin America could be used to improve the location of the SGDC with the TWSTFT links. The satellite location uncertainty is calculated using a geometry factor called PDOP. The results indicate that there is a way to accentuate the reduction of the PDOP and, consequently, decrease the location uncertainty of the geostationary satellite.","PeriodicalId":221354,"journal":{"name":"2022 IEEE Latin-American Conference on Communications (LATINCOM)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132268007","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 : 2022-11-30DOI: 10.1109/LATINCOM56090.2022.10000704
Luana Gantert, Matteo Sammarco, Marcin Detyniecki, M. Campista
Audio samples have emerged as a trend for monitoring and improving decision-making in smart cities, medical applications, and environmental event detections. This paper proposes a Super Learner ensemble application in two scenarios: to distinguish urban from domestic sounds, and detect abnormal samples in industrial machines. The Super Learner combines supervised classifiers to detect abnormal samples or determine a class of an event from spectral features extracted from original sounds. We study the impact on time processing and performance of varying the number of K-folds in the cross-validation step using the Environmental Sound Classification (ESC-50) and Malfunctioning Industrial Machine Investigation and Inspection (MIMII) datasets. The performance evaluation demonstrates that RF is the best classifier in the ESC-50 dataset and SVM in the MIMII dataset. However, the Super Learner reaches AUC and F1-Score values near the best algorithm in the majority of cases analyzed, representing the best tradeoff solution.
{"title":"Super Learner Ensemble for Sound Classification using Spectral Features","authors":"Luana Gantert, Matteo Sammarco, Marcin Detyniecki, M. Campista","doi":"10.1109/LATINCOM56090.2022.10000704","DOIUrl":"https://doi.org/10.1109/LATINCOM56090.2022.10000704","url":null,"abstract":"Audio samples have emerged as a trend for monitoring and improving decision-making in smart cities, medical applications, and environmental event detections. This paper proposes a Super Learner ensemble application in two scenarios: to distinguish urban from domestic sounds, and detect abnormal samples in industrial machines. The Super Learner combines supervised classifiers to detect abnormal samples or determine a class of an event from spectral features extracted from original sounds. We study the impact on time processing and performance of varying the number of K-folds in the cross-validation step using the Environmental Sound Classification (ESC-50) and Malfunctioning Industrial Machine Investigation and Inspection (MIMII) datasets. The performance evaluation demonstrates that RF is the best classifier in the ESC-50 dataset and SVM in the MIMII dataset. However, the Super Learner reaches AUC and F1-Score values near the best algorithm in the majority of cases analyzed, representing the best tradeoff solution.","PeriodicalId":221354,"journal":{"name":"2022 IEEE Latin-American Conference on Communications (LATINCOM)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121081990","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 : 2022-11-30DOI: 10.1109/LATINCOM56090.2022.10000774
M. Devigili, P. N. Goki, N. Sambo, P. Castoldi, L. Potí, A. D’Amico, V. Curri
Multi-band transmission is attracting the interest of research community because of its prospects to increase network infrastructures life. Indeed, current deployed systems mainly exploit the C band, thus deployed fibers can still offer a wide range of available spectrum. In this paper, quality of transmission (QoT) estimation is considered as fundamental control step for light path setup in order to check the proper feasibility of transmission along a computed light path. We demonstrate multi-band networking with channels on C and S bands in a testbed including a re-circulating loop. As a QoT estimator, the open-source GNPY module is extended in order to consider the typical impairments of a long-haul multi-band transmission and validated in this multi-band scenario for assisting connection setup with quality of transmission estimation. The measurements on the testbed demonstrated the correct operations of the multiband data plane testbed, particularly with reference to the GNPy estimations and thus validate the QoT estimator for C+S band transmission.
{"title":"Multi-band Optical Network Assisted by GNPy: an Experimental Demonstration","authors":"M. Devigili, P. N. Goki, N. Sambo, P. Castoldi, L. Potí, A. D’Amico, V. Curri","doi":"10.1109/LATINCOM56090.2022.10000774","DOIUrl":"https://doi.org/10.1109/LATINCOM56090.2022.10000774","url":null,"abstract":"Multi-band transmission is attracting the interest of research community because of its prospects to increase network infrastructures life. Indeed, current deployed systems mainly exploit the C band, thus deployed fibers can still offer a wide range of available spectrum. In this paper, quality of transmission (QoT) estimation is considered as fundamental control step for light path setup in order to check the proper feasibility of transmission along a computed light path. We demonstrate multi-band networking with channels on C and S bands in a testbed including a re-circulating loop. As a QoT estimator, the open-source GNPY module is extended in order to consider the typical impairments of a long-haul multi-band transmission and validated in this multi-band scenario for assisting connection setup with quality of transmission estimation. The measurements on the testbed demonstrated the correct operations of the multiband data plane testbed, particularly with reference to the GNPy estimations and thus validate the QoT estimator for C+S band transmission.","PeriodicalId":221354,"journal":{"name":"2022 IEEE Latin-American Conference on Communications (LATINCOM)","volume":"78 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114031884","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 : 2022-09-09DOI: 10.1109/LATINCOM56090.2022.10000692
Shaokai Hu, Hao Huang, Guan Gui, H. Sari
This paper analyzes the power imbalance issue in power-domain NOMA (PD-NOMA) in the presence of channel correlations, typically encountered on the downlink of cellular systems when the base station antennas have an insufficient separation. In a recent paper, the authors analyzed this issue for a typical uplink scenario with uncorrelated channels, and the study revealed an astounding result that the optimum in terms of average error probability is achieved when the user signals are perfectly balanced in terms of power as in multi-user MIMO with power control. This result led to some questioning of the concept of PD-NOMA for uncorrelated Rayleigh fading channels. In the present paper, we make a similar analysis for the downlink, and the study gives a very clear insight into the influence of the power imbalance at different levels of channel correlation. First, with full correlation (user signals transmitted from the same antenna), the PD-NOMA concept reduces to simple signal constellation design. The optimum is achieved when the power imbalance between the user signals is such that the resulting constellation has uniform spacing. Any deviation from this optimum will lead to a hierarchical constellation with performance loss. Also, this optimum power imbalance is shown to hold for a range of strong channel correlations, but for moderate and low correlation values perfectly power balanced NOMA takes over as in the presence of uncorrelated channels.
{"title":"Analysis of the Power Imbalance in Power-Domain NOMA on Correlated Rayleigh Fading Channels","authors":"Shaokai Hu, Hao Huang, Guan Gui, H. Sari","doi":"10.1109/LATINCOM56090.2022.10000692","DOIUrl":"https://doi.org/10.1109/LATINCOM56090.2022.10000692","url":null,"abstract":"This paper analyzes the power imbalance issue in power-domain NOMA (PD-NOMA) in the presence of channel correlations, typically encountered on the downlink of cellular systems when the base station antennas have an insufficient separation. In a recent paper, the authors analyzed this issue for a typical uplink scenario with uncorrelated channels, and the study revealed an astounding result that the optimum in terms of average error probability is achieved when the user signals are perfectly balanced in terms of power as in multi-user MIMO with power control. This result led to some questioning of the concept of PD-NOMA for uncorrelated Rayleigh fading channels. In the present paper, we make a similar analysis for the downlink, and the study gives a very clear insight into the influence of the power imbalance at different levels of channel correlation. First, with full correlation (user signals transmitted from the same antenna), the PD-NOMA concept reduces to simple signal constellation design. The optimum is achieved when the power imbalance between the user signals is such that the resulting constellation has uniform spacing. Any deviation from this optimum will lead to a hierarchical constellation with performance loss. Also, this optimum power imbalance is shown to hold for a range of strong channel correlations, but for moderate and low correlation values perfectly power balanced NOMA takes over as in the presence of uncorrelated channels.","PeriodicalId":221354,"journal":{"name":"2022 IEEE Latin-American Conference on Communications (LATINCOM)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132478608","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：