http://sedici.unlp.edu.ar:80/handle/10915/141024 Sun, 08 Nov 2026 23:41:00 GMT 2026-11-08T23:41:00Z http://sedici.unlp.edu.ar:80/handle/10915/141026 Objeto de conferencia VII Taller del Grupo de Trabajo de Ingeniería de Internet / Argentina (IETF Day 2021) - JAIIO 50 (Modalidad virtual) The objective of this work is to select machine learning classifiers for Network Intrusion Detection NIDS problems. The selection criterion is based upon the hyper-parameter variation, to evaluate and compare consistently the different models configuration. The models were trained and tested by crossvalidation sharing the same dataset partitions. The hyper-parameter search was performed in two ways, exhaustive and randomized upon the structure of the classifier to get feasible results. The performance result was tested for significance according to the frequentist and Bayesian significance test. The Bayesian posterior distribution was further analyzed to extract information in support of the classifiers comparison. The selection of a machine learning classifier is not trivial and it heavily depends on the dataset and the problem of interest. In this experiment seven classes of machine learning classifiers were initially analyzed, from which only three classes were selected to perform cross-validation to get the final selection, Decision Tree, Random Forest, and Multilayer Perceptron Classifiers. This article explores a systematic and rigorous approach to assess and select NIDS classifiers further than selecting the performance scores. Fri, 01 Jan 2021 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/141026 2021-01-01T00:00:00Z The objective of this work is to select machine learning classifiers for Network Intrusion Detection NIDS problems. The selection criterion is based upon the hyper-parameter variation, to evaluate and compare consistently the different models configuration. The models were trained and tested by crossvalidation sharing the same dataset partitions. The hyper-parameter search was performed in two ways, exhaustive and randomized upon the structure of the classifier to get feasible results. The performance result was tested for significance according to the frequentist and Bayesian significance test. The Bayesian posterior distribution was further analyzed to extract information in support of the classifiers comparison. The selection of a machine learning classifier is not trivial and it heavily depends on the dataset and the problem of interest. In this experiment seven classes of machine learning classifiers were initially analyzed, from which only three classes were selected to perform cross-validation to get the final selection, Decision Tree, Random Forest, and Multilayer Perceptron Classifiers. This article explores a systematic and rigorous approach to assess and select NIDS classifiers further than selecting the performance scores. http://sedici.unlp.edu.ar:80/handle/10915/141025 Objeto de conferencia VII Taller del Grupo de Trabajo de Ingeniería de Internet / Argentina (IETF Day 2021) - JAIIO 50 (Modalidad virtual) Vehicular Communication Networks (VCN) are critical enabling technologies that contribute to the advancement of Intelligent Transportation Systems. Although initially VCN were thought with a focus on safety, there is a myriad of IP-based applications for information and entertainment systems to be deployed in vehicular scenarios. To support IP-based applications, standard protocol stacks, including IEEE WAVE and the recent 3GPP C-V2X architectures, define the transport of IPv6 and related protocols on top of the specific wireless access technologies. One of the fundamental protocols for the use of IPv6 is Neighbor Discovery (ND), defined in RFC 4861. In this work, we evaluate the performance of the standard ND protocol and compare it to recent works, including several IETF Internet-drafts, that propose enhancements for the IP registration and duplicate detection processes in the dynamic environment of VCN. Fri, 01 Jan 2021 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/141025 2021-01-01T00:00:00Z Vehicular Communication Networks (VCN) are critical enabling technologies that contribute to the advancement of Intelligent Transportation Systems. Although initially VCN were thought with a focus on safety, there is a myriad of IP-based applications for information and entertainment systems to be deployed in vehicular scenarios. To support IP-based applications, standard protocol stacks, including IEEE WAVE and the recent 3GPP C-V2X architectures, define the transport of IPv6 and related protocols on top of the specific wireless access technologies. One of the fundamental protocols for the use of IPv6 is Neighbor Discovery (ND), defined in RFC 4861. In this work, we evaluate the performance of the standard ND protocol and compare it to recent works, including several IETF Internet-drafts, that propose enhancements for the IP registration and duplicate detection processes in the dynamic environment of VCN.