Proyectos archivo | Programa FRIDA

TinyML for Anomaly Detection using Programmable Data Planes in Software Defined Networking Architecture

To improve the security of software-defined networks, one of the most widely used approaches has been the development of intrusion detection systems (IDS) based on machine learning (ML) and deep learning (DL) models that are deployed at the level of control. However, given the way this approach operates, which is reactive and depends on sending information from data plane devices to the control plane, there are limitations in the scalability of the solution.

Despite the advantages offered by data plane programmability for anomaly detection using ML/DL models, the implementation of this approach is not trivial. Programmable switches face challenges due to their memory and processing and storage capacity constraints. For this reason, models implemented in the data plane must meet the condition of having low computational resource consumption, while maintaining high accuracy in anomaly detection. As an approach to address the challenges represented by these limitations, the use of so-called Tiny Machine Learning – TinyML has recently been proposed. TinyML is a paradigm that facilitates the use of ML on devices with limited processing and low memory capacity.

This project proposes the implementation of compressed ML/DL techniques developed using TinyML for the detection of DoS and DDoS attacks in programmable switches in a software-defined network. The objective is to validate the operation of these ML/DL techniques in the data plane, comparing metrics such as the accuracy in the detection of anomalies, and the consumption of resources in the switches.

DDoS ATTACK DETECTION IN COMPUTER NETWORKS BASED ON A JOINT STACKING ARCHITECTURE OF MACHINE LEARNING MODELS

Distributed denial of service (DDoS) is a frequent threat to computer networks due to its disruption of the services they offer. This disruption results in network instability and/or inoperability. There are different types of DDoS attacks, each with a different mode of operation, so that their detection has become a difficult task for network monitoring and control systems.

The joint stacking of Machine Learning (ML) models consists of establishing a two-layer architecture, where layer 0 (base models) consists of two or more different learning algorithms that are trained with the same data set, and layer 1 (metamodel), which is trained in the best way from the predictions of the base models to establish the final prediction.

This work is based on the exploration and selection of a data set that represents DDoS attack events and carrying out its treatment in a pre-processing phase, resulting in the training, validation and test data sets. Subsequently, in layer 0, a set of ML models will be instantiated to be trained. Once trained, predictions are made on the validation set. Finally, the base models make predictions on the test data set. These predictions feed the metamodel to make the final predictions and, consequently, obtain the metrics of the joint stacked model, such as accuracy, precision, recall, F1 score, confusion matrix, and ROC-AUC, among others. Throughout the training of the models, different configurations will be tested and the hyper-parameters that present a better result based on the proposed metrics will be chosen.

InteliGente: Building Paths of Equality with Artificial Intelligence

InteliGente is an innovative initiative dedicated to integrating AI into education, fostering equity, and personalizing learning experiences for diverse student needs. By empowering students to develop AI solutions for social good, we are advancing education, democratizing AI, and addressing disparities in access to technology, particularly in regions such as the Global South. The project’s main innovation lies in the integration of active learning methodologies with a focus on AI.

Furthermore, the project applies a problem-based learning approach, where students are challenged to develop AI solutions for real problems, promoting hands-on learning and applying theoretical knowledge. This method improves students’ understanding of AI and develops crucial skills such as critical thinking, problem-solving, and teamwork. Key competencies developed in the project include argumentation, communication, knowledge, empathy, planning, organization, teamwork, responsibility, citizenship, and scientific, critical, and creative thinking. Additionally, InteliGente aims to encourage participants to develop solutions that align with the Sustainable Development Goals (SDGs), such as (SDG 3) Good health and well-being; (SDG 4) Quality education; (SDG 5) Gender equality; (SDG 10) Reduced inequalities; and (SDG 13) Climate action.

Tec Para Todos: Expanding digital inclusion for the economic empowerment of rural and indigenous women in the Sierra Otomí-Tepehua-Nahua, Mexico

PSYDEH works with rural and indigenous women in the Sierra Otomí-Tepehua-Nahua region of Hidalgo, where they face severe socio economic challenges. PSYDEH currently implements two interconnected field programs. The Sierra Madre Network is a cooperative incubation program and a community leadership school. Tech for All is a digital inclusion program that addresses socioeconomic disparities in access to electricity, technology, and online tools in the isolated communities where we work.

In this context, PSYDEH proposes a project that builds on our core programming that links women’s economic empowerment with digital inclusion to increase the capacity of female partners to use Internet tools to develop, market, and sell their textiles and design a sustainable tourism route that brings economic and social benefits to the region. Key project activities include building two additional digital resource centers in the region, conducting basic computer skills workshops and a two-month intensive digital entrepreneurship course, supporting cooperatives in developing branding and marketing strategies, and developing a regional online sales platform where women can sell their products. They also involve promoting a pilot sustainable tourism route online and expanding that route through the use of online payment systems, digital design software and social media marketing.

Development of artificial intelligence models for attack detection based on data available on LACNIC’s Honeynet

Honeypots are software systems that emulate real services and monitor attacks against a specific network. They are systems that simulate being a target for attackers, and use the intrusion attempts of these cybercriminals to learn how they operate or simply to distract them and thus protect other assets. The deployment of honeypots on several physical machines makes up a honeynet. LACNIC’s Computer Security Incident Response Team (CSIRT) has an initiative called LACNIC Honeynet to obtain first-hand knowledge about the most common security threats in the Latin American and Caribbean region. This Honeynet is a very important asset for the development of cybersecurity strategies in the region.

In this line, the project seeks to create artificial intelligence models for the detection of intruders with the data collected from the already deployed honeynet, focusing on the type of attack that occurs most frequently in the region (e.g. ransomware, DDoS, phishing, etc.). This will allow the development of transferable solutions for the actors in the Internet ecosystem, thereby strengthening cyber intelligence and resilience in public and private institutions in Latin America and the Caribbean.

Computer Waste Management Plant of Node TAU / Right to a healthy environment, social and labor inclusion and digital inclusion

The Computer Waste Management Plant is a social enterprise promoted by Nodo Tau aimed at the environmentally correct management of technological waste, recovering materials for production, avoiding the extraction of natural environments and their contamination and promoting the creation of youth employment and the reuse of equipment for a second useful life, especially in community spaces.

The Computer Waste Management Plant is today an experience that grows in work, in training and in articulations with numerous institutions. The Plant today receives equipment from government entities and some companies, and from collection campaigns. Equipment that can be repaired begins a second useful life. Those that do not, are disassembled and their materials are recovered, saving the environmental impact that they would have if they were improperly disposed of or accumulated.

In 4 years of work at the Plant, its objectives have been to give waste proper environmental treatment, consolidate a work space for young people and recover equipment for social projects. Regarding specific indicators of this work, the project has some indicators that show what has been achieved, including more than 100 tons of WEEE treated, 700 computers recovered for a second useful life, 35 community spaces that received computers recovered in the plant and a work team made up of 8 young people who are going through their first work experience within the framework of the Santa Fe Más program and consolidating a productive unit, which is the only one in the city enabled to address this problem.

Yafun Project

Based on a proposal presented that allows progress towards total digital connectivity of the Chilean territory, the project sought to understand the problem of resilience (tolerance to faults, attacks and catastrophes) of the Internet in general and apply this knowledge. The objective was to make an innovative proposal to improve the country’s connectivity in terms of access, quality and resilience. Based on graph theory and optimization, and a cost-benefit analysis, the necessary routes and lines of trunk fiber optics were presented to ensure connectivity and resilience of all regions of the country.

The regulatory authority was able to offer subsidies to the supply for the development and deployment of this fiber optic infrastructure, allowing rural and extreme sectors to have the same technical feasibility as the metropolis.

This work has configured a map of national digital connectivity, which identifies the existing deployment of structuring fiber optics on main and secondary roads, along with details of 1,800 locations without Internet access.

Thanks to field research, carried out in 345 communes of the country, the research team has been able to collaborate with initiatives and connectivity projects of community and regional scope, developing actions required to shorten the national digital divide.

Citizen Laboratory for Gender Equity in ICT

This project proposes a set of activities designed from a gender perspective so that women and girls achieve an effective insertion into the digital world, based on a breakdown of gender digital gap indicators for rural areas with basic and advanced digital skills. In parallel, gender-based violence that is reproduced in the digital context such as cyberbullying, groming, revenge among others, which make the digital world an unsafe context for them, will be addressed, so that good practices are addressed from prevention and education, for a safe and equitable Internet, the development of inclusive IT solutions designed by women for the well-being of all citizens.

Promoting citizen digital innovation from a gender perspective, the Union of Informaticians of Cuba, based on a methodological proposal that allows promoting citizen digital innovation from a gender perspective, will work to educate the female universe at the local level, regarding the assimilation of basic and advanced digital skills; vocationally guiding adolescents and young people to study STEM specialties, digitally empowering women, adolescents and girls and will work on the development of professional skills of women and adolescents in pursuit of their incorporation into the labor market.

Assistance to Mayan leaders of the Digital Community Centers

New Sun Road Guatemala, S.A. has worked on the creation of twenty Digital Community Centers (CCDs) with solar energy and internet connectivity in rural communities with indigenous populations in Guatemala, more than two thousand women were trained in digital skills, video tutorials were generated in Q’eqchi and Chuj languages, more than two hundred women were trained to form the Women Leaders Committee and more than fourteen thousand services have been provided to the communities through the CCDs. To continue advancing in this objective, currently, the organization, through this initiative, seeks to provide support and technical assistance to the leaders of the twenty existing Centers in Huehuetenango and Alta Verapaz, strengthening digital skills with video tutorials and remote support in Q’eqchi’y Chuj , focused on existing artificial intelligence (AI) tools that help reduce language barriers for full use of the internet to support its users to improve their digital skills.

In addition to helping the conservation of these Mayan languages by digitizing them, the Committee of leaders will be supported to integrate a Commission of Digital Community Centers integrating the Cocodes, religious leaders, teachers, among other relevant actors to integrate workshops with playful activities that allow breaking gender stereotypes, raise awareness regarding positive masculinities in the community and mainly include the relatives of the leaders so that they can help with shared tasks at home and support them in their full use of the internet.

Creating capacities for women and girls in the Chitara Cerritana: We are Guardians of the Páramo

This project seeks the implementation of wireless and sustainable communication technologies in the local communities of the Almorzadero páramo, including community radios, satellite communication systems and long-distance communication networks based on WIFi, seeking to improve connectivity and communication between the páramo communities, which will help promote social, economic and cultural development in these isolated areas of peasant tradition. In addition, these communication networks will be used to facilitate the coordination and exchange of information on the conservation and management of natural resources in the páramo, which will contribute to the protection and conservation of these valuable ecosystems.

Thus, the project focuses on promoting the use, management and community participation of peasant women in a wireless Community Network to guarantee communication in their territory as well as Internet access, giving workshops for self-management of the network and benefiting the more than 250 associated women who for nearly 17 years have been forging and strengthening their peasant and community organization. In this way, Colnodo and the members of the community themselves will be able to contribute to such an important undertaking, holding workshops to identify their needs with them and propose solutions that can be provided jointly with the community, strengthening local productive capacities and raising awareness about the risks related to the Internet and information and communication technologies, especially those that affect women and girls. Through a participatory approach that involves community members in all stages of the project, from planning to implementation and maintenance, activities such as training workshops, infrastructure installation, and network performance monitoring will be carried out

Through a participatory approach where community members will be involved in all stages of the project, from planning to implementation and maintenance, activities such as training workshops, infrastructure installation and monitoring of network performance will be carried out.