IMDEA Networks Institute Digital Repository
Not a member yet
1915 research outputs found
Sort by
Multivariate Functional Outlier Detection using the FastMUOD Indices
Get PDFWe present definitions and properties of the fast massive unsupervised outlier detection (FastMUOD) indices, used for outlier detection (OD) in functional data. FastMUOD detects outliers by computing, for each curve, an amplitude, magnitude and shape index meant to target the corresponding types of outliers. Some methods adapting FastMUOD to outlier detection in multivariate functional data are then proposed. These include applying FastMUOD on the components of the multivariate data and using random projections. Moreover, these techniques are tested on various simulated and real multivariate functional datasets. Compared with the state of the art in multivariate functional OD, the use of random projections showed the most effective results with similar, and in some cases improved, OD performance.Comunidad de MadridMinisterio de Economía, Industria y CompetitividadREACT-EU funds from the European regional development fund “a way of making Europe”FSE & FEDERTRUEpu
Label-Aware Aggregation for Improved Federated Learning
Get PDFFederated Averaging (FedAvg) is the most common aggregation method used in Federated learning, which performs a weighted averaging of the updates based on the sizes of the individual datasets of each client. A raising discussion in the research community suggests that FedAvg might not be the optimal method since, for instance, it does not fully take into account the variety of the client data distributions. In this paper, we propose a label-aware aggregation method FedLA, that addresses the biased models issue by considering the variety of labels in the weighted averaging. It combines two main properties of the client data, namely data size and label distribution. Through extensive experiments, we demonstrate that FedLA is particularly effective in several heterogeneous data distribution scenarios. Especially when only a small group of the clients is participating in the Federated Learning process. Furthermore, we argue that accurately describing the data distribution is crucial in selecting the appropriate aggregation method. In this regard, we discuss various properties that can be used to describe data distribution and illustrate how these properties can guide the choice of an aggregation method for specific data distributions.TRUEpu
SkyPos: Real-world evaluation of self-positioning with aircraft signals for IoT devices
Get PDFPositioning based on aircraft signals has been proposed as an alternative to satellite-based positioning systems (e.g. GPS). However, so far, no deployment of this technique exists, and the real-world performance remains unclear. This paper contributes at better understanding the performance tradeoffs under realistic conditions. We implement SkyPos, a localization system for GPS-denied areas or location integrity that opportunistically uses the large availability of aircraft signals to self-localize receivers. We analyze SkyPos with data collected from hundreds of sensors and thousands of aircraft around Europe. Our results show that we can achieve median accuracy down to 10\,m in seconds, enabling almost real-time positioning or location verification using aircraft signals at scale.armasuisseMinistry of Universities (FPU)TRUEpu
Improving Blockchain Scalability with the Setchain Data-type
Get PDFBlockchain technologies are facing a scalability challenge, which must be overcome to guarantee a wider adoption of the technology. This scalability issue is due to the use of consensus algorithms to guarantee the total order of the chain of blocks (and of the transactions within each block). However, total order is often not fully necessary, since important advanced applications of smart-contracts do not require a total order among all operations. A much higher scalability can potentially be achieved if a more relaxed order (instead of a total order) can be exploited.
In this paper, we propose a novel distributed concurrent data type, Setchain, which significantly improves scalability. A Setchain implements a grow-only set whose elements are not ordered, unlike conventional blockchain operations. When convenient, the Setchain allows forcing a synchronization barrier that assigns permanently an epoch number to a subset of the latest elements added, agreed by consensus. Therefore, two operations in the same epoch are not ordered, while two operations in different epochs are ordered by their respective epoch number. We present different Byzantine-tolerant implementations of Setchain, prove their correctness and report on an empirical evaluation of a prototype implementation. Our results show that Setchain is orders of magnitude faster than consensus-based ledgers, since it implements grow-only sets with epoch synchronization instead of total order.
Since the Setchain barriers can be synchronized with the underlying blockchain, Setchain objects can be used as a sidechain to implement many decentralized solutions with much faster operations than direct implementations on top of blockchains.
Finally, we also present an algorithm that encompasses into a single process the combined behavior of the Byzantine servers, which simplifies correctness proofs by encoding the general attacker in a concrete implementation.TRUEpu
Characterizing Mobile Service Demands at Indoor Cellular Networks
Get PDFIndoor cellular networks (ICNs) are anticipated to become a princi-pal component of 5G and beyond systems. ICNs aim at extendingnetwork coverage and enhancing users’ quality of service and ex-perience, consequently producing a substantial volume of trafficin the coming years. Despite the increasing importance that ICNswill have in cellular deployments, there is nowadays little under-standing of the type of traffic demands that they serve. Our workcontributes to closing that gap, by providing a first characterizationof the usage of mobile services across more than 4, 500 cellular an-tennas deployed at over 1, 000 indoor locations in a whole country.Our analysis reveals that ICNs inherently manifest a limited setof mobile application utilization profiles, which are not present inconventional outdoor macro base stations (BSs). We interpret theindoor traffic profiles via explainable machine learning techniques,and show how they are correlated to the indoor environment. Ourfindings show how indoor cellular demands are strongly dependenton the nature of the deployment location, which allows anticipatingthe type of demands that indoor 5G networks will have to serveand paves the way for their efficient planning and dimensioning.TRUEinpres
In the Room Where It Happens: Characterizing Local Communication and Threats in Smart Homes
Get PDFThe network communication between Internet of Things (IoT) devices on the
same local network has significant implications for platform
and device interoperability, security, privacy, and
correctness. Yet, the analysis of local home Wi-Fi network traffic and
its associated security and privacy threats have been largely ignored
by prior literature, which typically focuses on studying the communication
between IoT devices and cloud end-points, or detecting vulnerable IoT devices
exposed to the Internet. In this paper, we present a comprehensive and empirical
measurement study to shed light on the local communication within a smart
home deployment and its threats. We use a unique combination of
passive network traffic captures, protocol honeypots, dynamic mobile app analysis,
and crowdsourced IoT data from participants to identify and analyze a
wide range of device activities on the
local network. We then analyze these datasets to characterize local
network protocols, security and privacy threats associated with them.
Our analysis reveals vulnerable devices, insecure use of network protocols,
and sensitive data exposure by IoT devices.
We provide evidence of how this information is
exfiltrated to remote servers by mobile apps and third-party SDKs,
potentially for household fingerprinting, surveillance and cross-device tracking.
We make our datasets and analysis
publicly available to support further research in this area.TRUEinpres
Performance and Explainability of Feature Selection-Boosted Tree-based Classifiers for COVID-19 Detection
Get PDFIn this paper, we evaluate the performance and analyze the explainability of machine learning models boosted by feature selection in predicting COVID-19-positive cases from self-reported information. In essence, this work describes a methodology to identify COVID-19 infections that considers the large amount of information collected by the University of Maryland Global COVID-19 Trends and Impact Survey (UMD-CTIS). More precisely, this methodology performs a feature selection stage based on the recursive feature elimination (RFE) method to reduce the number of input variables without compromising detection accuracy. A tree-based supervised machine learning model is then optimized with the selected features to detect COVID-19-active cases. In contrast to previous approaches that use a limited set of selected symptoms, the proposed approach builds the detection engine considering a broad range of features including self-reported symptoms, local community information, vaccination acceptance, and isolation measures, among others. To implement the methodology, three different supervised classifiers were used: random forests (RF), light gradient boosting (LGB), and extreme gradient boosting (XGB). Based on data collected from the UMD-CTIS, we evaluated the detection performance of the methodology for four countries (Brazil, Canada, Japan, and South Africa) and two periods (2020 and 2021). The proposed approach was assessed in terms of various quality metrics: F1-score, sensitivity, specificity, precision, receiver operating characteristic (ROC), and area under the ROC curve (AUC). This work also shows the normalized daily incidence curves obtained by the proposed approach for the four countries. Finally, we perform an explainability analysis using Shapley values and feature importance to determine the relevance of each feature and the corresponding contribution for each country and each country/year.Comunidad de MadridSpanish Ministry of Science and InnovationEuropean Union "Next Generation EU"Shapley ValuesTRUEpu
Showcasing In-Switch Machine Learning Inference
Get PDFRecent endeavours have enabled the integration of trained machine learning models like Random Forests in resource-constrained programmable switches for line rate inference. In this work, we first show how packet-level information can be used to classify individual packets in production-level hardware with very low latency. We then demonstrate how the newly proposed Flowrest framework improves classification performance relative to the packet-level approach by exploiting flow-level statistics to instead classify traffic flows entirely within the switch without considerably increasing latency. We conduct experiments using measurement data in a real-world testbed with an Intel Tofino switch and shed light on how Flowrest achieves an F1-score of 99% in a service classification use case, outperforming its packet-level counterpart by 8%.European Union Horizon 2020 research and innovation program under grant agreement no. 101017109 “DAEMON”European Union Horizon 2020 research and innovation program under Marie Skłodowska-Curie grant agreement no. 860239 “BANYAN”CHIST-ERA grant no. CHIST-ERA-20-SICT- 001 “ECOMOME”, via grant PCI2022-133013 of Agencia Estatal de InvestigaciónBest Demo AwardTRUEpu
Enabling Network and Service Programmability in 6G Mobile Communication Systems
Get PDFNetwork programmability is crucial for addressing the multiplicity and heterogeneity of Network Services, the diversity of the underlying infrastructure of Sixth-Generation (6G) communication systems, and the requirements for maximum efficiency. The programmability of a service platform enables algorithmic network management by leveraging contemporary software virtualization technologies. Moreover, network programmability will abstract the essential network/service and resource configuration, as well as the production and administration of policy lifecycles, as the number of local breakouts (both public and private) is anticipated to grow exponentially. Network programmability is the central point of interest for Hexa-X, the European 6G flagship project, which aims to facilitate the dynamic adaptation to changing network situations and requirements for the most efficient use of available resources. To explore such a critical enabler of futuristic mobile networks, this article addresses the role of network and service programmability and its impact on various aspects of 6G within the context of Hexa-X. In order to accomplish this, the article begins by discussing Hexa-X's proposed service Management and Orchestration (M&O) framework for 6G. Based on this framework, it identifies and explores in greater detail the programmability of four primary processes in 6G: expressing application and service requirements; service description models and profiling; monitoring and diagnostics; and reasoning. Beyond the scope of the Hexa-X, this article aims to serve as a foundation for future research into network and service programmability in 6G.TRUEpu
Image Watermarking for Machine Learning Datasets
Get PDFMachine learning has received increasing attention for the last decade due to its significant success in classification problems in almost every application domain. For its success, the amount of available data for training plays a crucial role in the creation of a machine-learning model. However, the data-gathering process for machine learning algorithms is a tedious and time-consuming task. In many cases, the developers rely on publicly available datasets, which are not always of high quality. Recently, we are witnessing a data market paradigm where valuable datasets are sold. Thus, once the dataset is created or bought, protecting the dataset against illegal use or (re)sale and establishing intellectual property rights is necessary. In this paper, we investigate the question of deploying well- studied image watermarking techniques to be applied to classification algorithm datasets, without degrading the quality of the dataset. We investigate whether Singular Value Decomposition (SVD)-based techniques from image watermarking could be deployed on machine learning datasets or not. To this end, we chose the watermarking technique described in [8] and applied it to a machine-learning dataset. We provide experimental results on the robustness of the scheme. Our results show that the watermark embedding scheme provides decent imperceptibility and robustness against update, zero- out, and insertion attacks but, it is not successful against deletion attacks. We believe our work can inspire researchers who might want to consider applying well-studied image watermarking techniques to machine learning datasetsTRUEpu