The great commitment in different areas of computer science for the study of computer networks used to fulfill specific and major business tasks has generated a need for their maintenance and optimal operability. Distributed denial of service (DDoS) is a frequent threat to computer networks because of its disruption to the services they cause. This disruption results in the instability and/or inoperability of the network. There are different classes of DDoS attacks, each with a different mode of operation, so detecting them has become a difficult task for network monitoring and control systems. The objective of this work is based on the exploration and choice of a set of data that represents DDoS attack events, on their treatment in a preprocessing phase, and later, the generation of a model of sequential neural networks of multi-class classification. This is done to identify and classify the various types of DDoS attacks. The result was compared with previous works treating the same dataset used herein. We compared their classification method, against ours. During this research, the CIC DDoS2019 dataset was used. Previous works carried out with this dataset proposed a binary classification approach, our approach is based on multi-classification. Our proposed model was capable of achieving around 94% in metrics such as precision, accuracy, recall and F1 score. The added value of multiclass classification during this work is identified and compared with binary classifications using the models presented in the previous.

Mobile Ad Hoc Networks (MANETs) are multihop wireless networks of mobile nodes without any fixed or preexisting infrastructure. The topology of these networks can change randomly due to the unpredictable mobility of nodes and their propagation characteristics. In most networks, including MANETs, each node needs a unique identifier to communicate. This work presents a distributed protocol for dynamic node IP address assignment in MANETs. Nodes of a MANET synchronize from time to time to maintain a record of IP address assignments in the entire network and detect any IP address leaks. The proposed stateful autoconfiguration scheme uses the OLSR proactive routing protocol for synchronization and guarantees unique IP addresses under a variety of network conditions, including message losses and network partitioning. Simulation results show that the protocol incurs low latency and communication overhead for IP address assignment.

The TCP/IP protocol allows the different nodes in a network to communicate by associating a different IP address to each node. In wired or wireless networks with infrastructure, we have a server or node acting as such which correctly assigns IP addresses, but in mobile ad hoc networks there is no such centralized entity capable of carrying out this function. Therefore, a protocol is needed to perform the network configuration automatically and in a dynamic way, which will use all nodes in the network (or part thereof) as if they were servers that manage IP addresses. This article reviews the major proposed auto-configuration protocols for mobile ad hoc networks, with particular emphasis on one of the most recent: D2HCP. This work also includes a comparison of auto-configuration protocols for mobile ad hoc networks by specifying the most relevant metrics, such as a guarantee of uniqueness, overhead, latency, dependency on the routing protocol and uniformity.

With the rise of social networks and the introduction of data protection laws, companies are training machine learning models using data generated locally by their users or customers in various types of devices. The data may include sensitive information such as family information, medical records, personal habits, or financial records that, if leaked, can generate problems. For this reason, this paper aims to introduce a protocol for training Multi-Layer Perceptron (MLP) neural networks via combining federated learning and homomorphic encryption, where the data are distributed in multiple clients, and the data privacy is preserved. This proposal was validated by running several simulations using a dataset for a multi-class classification problem, different MLP neural network architectures, and different numbers of participating clients. The results are shown for several metrics in the local and federated settings, and a comparative analysis is carried out. Additionally, the privacy guarantees of the proposal are formally analyzed under a set of defined assumptions, and the added value of the proposed protocol is identified compared with previous works in the same area of knowledge.

Establishing reliable and efficient multicast services in heterogeneous networks under an erasure channel is one of the current priorities in coding theory, particularly in Network Coding (NC) over data networks. Additionally, the increasing number of clients with mobile devices with high processing capabilities and the prevalence of non-delay tolerant traffic have led to the demand for non-feedback multicast schemes regarding distributed resource management. Current communication platforms lack gradual and dynamic coding control based on the type of data being transmitted. This paper proposes a reliable transmission scheme based on a concatenation of systematic coding and Random Linear Network Coding (RLNC) called Fulcrum coding. This hybrid rateless coding scheme with distributed characteristics allows the implementation of an adaptive resource management system to increase the decoding probability during data reception. The method ultimately results in a higher network throughput and shorter transmission times (RTT) per packet by implementing efficient Forward Error Correction (FEC).