IMDEA Networks Institute Digital Repository
Not a member yet
1915 research outputs found
Sort by
Explainable Machine Learning for Performance Anomaly Detection and Classification in Mobile Networks
Get PDFMobile communication providers continuously collect many parameters, statistics, and key performance indicators (KPIs) with the goal of identifying operation scenarios that can affect the quality of Internet-based services. In this regard, anomaly detection and classification in mobile networks have become challenging tasks due to both the huge number of involved variables and the unknown distributions exhibited by input features. This paper introduces an unsupervised methodology based on both a data-cleaning strategy and explainable machine learning models to detect and classify performance anomalies in mobile networks. Specifically, this methodology dubbed explainable machine learning for anomaly detection and classification (XMLAD) aims at identifying features and operation scenarios characterizing performance anomalies without resorting to parameter tuning. To this end, this approach includes a data cleaning stage that extracts and removes outliers from experiments and features to train the anomaly detection engine with the cleanest possible dataset. Moreover, the methodology considers the differences between discretized values of the target KPI and labels predicted by the anomaly detection engine to build the anomaly classification engine which identifies features and thresholds that could cause performance anomalies. The proposed methodology incorporates two decision tree classifiers to build explainable models of anomaly detection and classification engines whose decision structures recognize features and thresholds describing both normal behaviors and performance anomalies. We evaluate the XMLAD methodology on real datasets captured by operational tests in commercial networks. In addition, we present a testbed that generates synthetic data using a known TCP throughput model to assess the accuracy of the proposed approach.Spanish State Research Agency - Spanish Ministry of Science and InnovationMinistry of Economic Affairs and Digital Transformation, European Union NextGeneration-EUDepartment of Education and Research of the Regional Government of Madrid, through the 2018 R&D technology program for research groups, co-financed by the Operational Programs of the European Social Fund (ESF) and the European Regional Development Fund (ERDF)Nokia SpainTRUEpu
A Simulation Tool for Interference Analysis in MIMO Wavelength Division LiFi Indoor Networks
Get PDFIn this paper we propose a novel simulation tool for indoor Light Fidelity (LiFi) networks based on Wavelength Division (WD) with real optical filters characteristics. Firstly we present the measured passband spectra of optical filters, along with a system model validation relying on such acquired spectra. Secondly, we propose a simulation tool developed to extend the work of adaptive wavelength division multiple access to the multiple-input multiple-output case, suitable for conducting Monte Carlo simulations. Then, we validate such tool by considering an example scenario with fixed positions and orientations, including increasing number of users in an indoor LiFi network using WD. In order to better clarify the interference contributions to the quality of service provided, we consider the first user as reference, and evaluate how the presence of progressively higher number of users in its vicinity impacts the interference
that the main user is experiencing. We then analyse how the signal-to-interference-plus-noise ratio, interference-to-noise ratio and signal-to-interference ratio figures of the main user change depending on how many interfering users are included in the considered scenario.TRUEpu
Chrowned by an Extension: Abusing the Chrome DevTools Protocol through the Debugger API
Get PDFThe Chromium open-source project has become
a fundamental piece of the Web as we know it today, with
multiple vendors offering browsers based on its codebase.
One of its most popular features is the possibility of altering
or enhancing the browser functionality through third-party
programs known as browser extensions. Extensions have
access to a wide range of capabilities through the use of
APIs exposed by Chromium. The Debugger API—arguably
the most powerful of such APIs—allows extensions to use the
Chrome DevTools Protocol (CDP), a capability-rich tool for
debugging and instrumenting the browser. In this paper, we
describe several vulnerabilities present in the Debugger API
and in the granting of capabilities to extensions that can be
used by an attacker to take control of the browser, escalate
privileges, and break context isolation. We demonstrate their
impact by introducing six attacks that allow an attacker
to steal user information, monitor network traffic, modify
site permissions (e.g., access to camera or microphone),
bypass security interstitials without user intervention, and
change the browser settings. Our attacks work in all major
Chromium-based browsers as they are rooted at the core
of the Chromium project. We reported our findings to the
Chromium Development Team, who already fixed some of
them and are currently working on fixing the remaining
ones. We conclude by discussing how questionable design
decisions, lack of public specifications, and an overpowered
Debugger API have contributed to enabling these attacks,
and propose mitigations.TRUEinpres
In-depth analysis of the Android supply chain : Vendor customizations on critical networking components
Get PDFThe openness and extensibility of the Android Open Source Project (AOSP) enable An-
droid device vendors (also known as Original Equipment Manufacturers) to introduce
customizations in their products for market differentiation and adding new capabili-
ties. However, these customizations can have significant and severe implications for
user’s security and privacy.
The security and privacy risks caused by the lack of control over the Android supply
chain have caught the attention of cybersecurity researchers. Previous studies have
focused on analyzing the security issues related to pre-installed applications and
modifications made to the Android root store or network configurations. However,
a significant research gap exists due to the lack of investigation into how vendor
customizations on Android’s network stack can hinder the establishment of secure
network communications.
To assess the threats to secure communication introduced by vendors, I study the
customizations on the TLS/SSL protocol stack. I employ advanced static analysis
techniques, specifically diffing on Android firmware data gathered through crowd-
sourcing campaigns. By applying my static analysis pipeline over a dataset of 48,520
devices from more than 300 vendors, I detect and analyze vendor’s deviations from
the official Android Open Source Project (AOSP), maintained by Google. By ana-
lyzing the identified customizations, I uncover critical security vulnerabilities that
can compromise users’ and application’s security. These range from poor vendor
practices such as using older Android platform releases, delayed critical security
patches, outdated cryptographic implementations, insecure distributions of crypto-
graphic providers like vulnerable versions of OpenSSL to the absence of advanced
security functions such as certificate validation, hostname verification, and priori-
tized ciphersuites due to vendors’ removal of standard public methods offering these
capabilities.
Notably these shortcoming are persistent both within Android certified vendors as
well as non-certified ones. This suggests a total lack of control over the supply chain
and their compliance with best practices that directly impact on app developers’ at-
tempts to secure their applications using the native protocol stack. The preliminary
findings reported in this dissertation, highlight the need for stricter controls over the
Android supply chain. In fact, I believe that regulators and certification authorities
can promote new initiatives to strengthen device security guarantees and control the
practices of the different actors in the Android supply chain.Departamento de Sistemas Telemáticos y Computación (GSYC)IMDEA Network
Few-Shot Domain Adaptation for End-to-End Communication
Get PDFThe problem of end-to-end learning of a communication system using an autoencoder – consisting of an encoder, channel, and decoder modeled using neural networks – has recently been shown to be an effective approach. A challenge faced in the practical adoption of this learning approach is that under changing channel conditions (e.g. a wireless link), it requires frequent retraining of the autoencoder in order to maintain a low decoding error rate. Since retraining is both time consuming and requires a large number of samples, it becomes impractical when the channel distribution is changing quickly. We propose to address this problem using a fast and sample-efficient (few-shot) domain adaptation method that does not change the encoder and decoder networks. Different from conventional training-time unsupervised or semi-supervised domain adaptation, here we have a trained autoencoder from a source distribution that we want to adapt (at test time) to a target distribution using only a small labeled dataset, and no unlabeled data. We focus on a generative channel model based on the Gaussian mixture density network (MDN), and propose a regularized, parameter-efficient adaptation of the MDN using a set of affine transformations. The learned affine transformations are then used to design an optimal transformation at the decoder input to compensate for the distribution shift, and effectively present to the decoder inputs close to the source distribution. Experiments on many simulated distribution changes common to the wireless setting, and a real mmWave FPGA testbed demonstrate the effectiveness of our method at adaptation using very few target domain samples.Ministerio de Asuntos Económicos y Transformación DigitalMinisterio de Asuntos Económicos y Transformación DigitalComunidad de MadridTRUEpu
France Through the Lens of Mobile Traffic Data
Get PDFMobile usage data have shown unprecedented potential for data-driven research in various fields such as demography, sociology, geography, urban studies, criminology, and engineering. However, the lack of reference datasets limits research methods, results, verifiability, and reproducibility of outcomes hindering innovation opportunities. We release a novel mobile usage dataset offering a rare opportunity for the multidisciplinary research community to access rich mobile data of the spatiotemporal consumption of mobile applications in a developed country. The generation process of the dataset forms a new quality standard, leading to information about the demands generated by 68 popular mobile services, geo-referenced at a high resolution of 100x100 m2 over 20 metropolitan areas in France and monitored during 77 consecutive days in 2019.Comunidad de MadridFrench National Research Agency (ANR)TRUEinpres
Graph Database Watermarking Using Pseudo-Nodes
Get PDFWatermarking is used as proof of ownership for various data types such as images, videos, software, machine learning models, and databases. Datasets are crucial for data driven decision making using Machine Learning for tasks like prediction, recommendation, classification, and anomaly detection. Hence, it is not surprising that entire databases are being sold in data marketplaces. Protect- ing ownership rights upon such databases is, therefore, becoming increasingly important. Watermarking for relational databases has been an active field of research since 2002. However, how to water- mark non-relational databases involving complex data types has largely remained understudied. In this paper we revise previously proposed techniques for non-relational database watermarking and introduce an improved technique for graph database watermarking inspired by Zhuang et al. [28]. Our technique employs randomiza- tion to generate a watermark in an efficient manner that avoids the computational complex genetic algorithm optimization of Zhuang et al. We evaluated our technique in terms of performance, usability, security, and robustness by implementing it as a proof-of-concept. Our results showed that our technique is efficient, secure and robust against guessing and deletion attacks.TRUEpu
Fundamental Limits of Topology-Aware Shared-Cache Networks
Get PDFThis work studies a well-known shared-cache coded caching scenario where each cache can serve an arbitrary number of users. We analyze the case where there is some knowledge about such number of users (i.e., the topology) during the content placement phase. Under the assumption of regular placement and a cumulative cache size that can be optimized across the different caches, we derive the fundamental limits of performance by introducing a novel cache-size optimization and placement scheme and a novel information-theoretic converse. The converse employs new index coding techniques to bypass traditional uniformity requirements, thus finely capturing the heterogeneity of the problem, and it provides a new approach to handle asymmetric settings. The new fundamental limits reveal that heterogeneous topologies can in fact outperform their homogeneous counterparts where each cache is associated to an equal number of users. These results are extended to capture the scenario of topological uncertainty where the perceived/estimated topology does not match the true network topology. This scenario is further elevated to the stochastic setting where the user-to-cache association is random and unknown, and it is shown that the proposed scheme is robust to such noisy or inexact knowledge on the topology.Comunidad de Madrid - Atracción de talentoTRUEpu
DuctiLoc: Energy-efficient Location Sampling with Configurable Accuracy
Get PDFMobile device tracking technologies based on various positioning systems have made location data collection ubiquitous. The frequency at which location samples are recorded varies across applications, yet it is usually pre-defined and fixed, resulting in redundant information, and draining the battery of mobile devices. In this paper, we first answer the question “at what frequency should individual human movements be sampled so that they can be reconstructed with minimum loss of information?”. Our analysis unveils a novel linear scaling law of the localization error with respect to the sampling interval. We then present DuctiLoc, a location sampling mechanism that utilises the law above to profile users and adapt the position tracking frequency to their mobility. DuctiLoc is energy efficient, as it does not rely on power- hungry sensors or expensive computations; moreover, it provides a handy knob to control energy usage, by configuring the target positioning accuracy. Controlling the trade-off between accuracy and sampling rate of human movement is useful in a number of contexts, including mobile computing and cellular networks. Real-world experiments with an Android implementation show that DuctiLoc can effectively adjust the sampling frequency to individual mobility habits and target accuracy level, reducing the energy consumption by 60% to 98% with respect to a baseline periodic sampling.Regional Government of MadridTRUEpu
Adaptive Uplink Data Compression in Spectrum Crowdsensing Systems
Get PDFUnderstanding spectrum activity is challenging
when attempted at scale. The wireless community has recently
risen to this challenge in designing spectrum monitoring systems
that utilize many low-cost spectrum sensors to gather large
volumes of sampled data across space, time, and frequencies.
These crowdsensing systems are limited by the uplink bandwidth
available to backhaul the raw in-phase and quadrature (IQ)
samples and power spectrum density (PSD) data needed to run
various applications. This paper presents FlexSpec, a framework
based on the Walsh-Hadamard transform to compress spectrum
data collected from distributed and low-cost sensors for real-time
applications. This transformation allows sensors to significantly
save uplink bandwidth thanks to its inherent properties both
when it is applied to IQ and PSD data. Additionally, by leveraging
a feedback loop between the sensor and the edge device it
connects to, FlexSpec carefully adapts the compression ratio over
time to changes in the spectrum and different applications, jointly
considering data size, application performance, and spectrum
variations. We experimentally evaluate FlexSpec in several applications.
Our results show that FlexSpec is particularly suitable for
IoT transmissions and signals close to the noise floor. Compared
with prior work, FlexSpec provides up to 7x more reduction
of uplink data size for signal detection based on PSD data, and
reduces up to 6x to 8x the number of undecodable messages
for IQ sample decoding.TRUEpu