Search

International audience

Internet eXchange Points (IXPs) play a major role in Internet connectivity. They provide an infrastructure for traffic exchange, attracting Internet Service Providers (ISPs), Content Delivery Networks (CDNs) and cloud providers, leading to a plethora of options for network operators to connect. Alongside, policymakers are interested in understanding how failures of these infrastructures could affect the cyber economy. In this paper, we propose a new method based on anycast to assess the importance of IXPs in terms of coverage and regional representativeness with the goal of predicting the impact of IXP failures. We deployed an anycast infrastructure to connect to major IXPs, simulate outages, and map the impact of such failures. Our experiments show that our methodology can predict how the traffic flows when one IXP goes down, helping operators get prepared to deal with these events, and add more information to better assess the importance of IXPs as a critical infrastructure.

Anycast routing has attracted interest in recent years as a technology for CDNs and anti-DDoS services. Most anycast studies conducted in the past relied on coarse measurement data, or are subjected to the collaboration of a global player affecting the experiment flexibility. In this paper, we present TANGLED, an anycast testbed where researchers can run experiments and better understand the impacts of their proposals on a global infrastructure. We also share our hand-on experience validating transit providers routing configurations. Our testbed offers a flexible and complete testing environment to evaluate the routing behavior of anycast networks in the wild. We provided tools that allow users to customize and reconFigure the anycast network, perform experiments, do active measurements, and collect data by using a platform specially designed for. The deployed infrastructure was designed to create industry and academy cooperation. TANGLED enables researchers to answer your research questions while allows transit providers to validate the implementation of complex routing agreements.

Critical networked services enable significant revenue for network operators and, in turn, are regulated by Service Level Agreements (SLAs). In order to ensure SLAs are being met, service levels need to be monitored. One technique for this involves active measurement mechanisms which employ measurement probes along the network to inject synthetic traffic and compute the network performance. However, these mechanisms are expensive in terms of resources consumption. Thus, these mechanisms usually can cover only a fraction of what could be measured, which can lead to SLA violations being missed. Besides that, the definition of this fraction is a practice done by human administrators, which does not scale well and does not adapt to highly dynamic networking patterns. In this article, we examine the potential benefits of using P2P technology to improve the detection of SLA Violations. We first describe the principles of a P2P-based steering of active measurement mechanisms. These principles are characterized by a high degree of decentralized decision making across a network using a self-organizing overlay. In a second step, we present measurement session activation strategies based on these principles. These strategies do not require human intervention, are adaptive to changes in network conditions, and independent of the underlying active measurement technology.

Advanced wireless services and applications are demanding lower latency and better reliability. In IEEE 802.11 networks, slicing abstractions at the Medium Access Control (MAC) layer can provide precise resource allocation and traffic isolation as a means to meet these performance requirements. In this paper, we propose a delay-aware approach for MAC management via airtime-based network slicing and user association using Multi-Criteria Decision Analysis (MCDA) in IEEE 802.11 Software-Defined Radio Access Networks (SD-RANs). To enable such an approach, we leverage Software-Defined Networking (SDN) to monitor queueing delay statistics at the Access Points (APs). We evaluate our approach in a testbed with two APs, controlled by SD-RAN and SDN controllers with four Stations (STAs) served by both Quality of Service (QoS) and Best-Effort (BE) flows dynamically. We compare our approach to a state-of-the-art user association approach. Our results show that in addition to load balancing flows across APs, our approach enhances the QoS delivery at runtime using slicing.

The 2019 Coronavirus disease (COVID-19) pandemic, caused by a quick dissemination of the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), has had a deep impact worldwide, both in terms of the loss of human life and the economic and social disruption. The use of digital technologies has been seen as an important effort to combat the pandemic and one of such technologies is contact tracing applications. These applications were successfully employed to face other infectious diseases, thus they have been used during the current pandemic. However, the use of contact tracing poses several privacy concerns since it is necessary to store and process data which can lead to the user/device identification as well as location and behavior tracking. These concerns are even more relevant when considering nationwide implementations since they can lead to mass surveillance by authoritarian governments. Despite the restrictions imposed by data protection laws from several countries, there are still doubts on the preservation of the privacy of the users. In this article, we analyze the privacy features in national contact tracing COVID-19 applications considering their intrinsic characteristics. As a case study, we discuss in more depth the Brazilian COVID-19 application Coronav��rus-SUS, since Brazil is one of the most impacted countries by the current pandemic. Finally, as we believe contact tracing will continue to be employed as part of the strategy for the current and potential future pandemics, we present key research challenges., 7 pages, 3 figures, to be translated to Portuguese and submitted to the Regional Computer Networking Conference