arXiv subjects

Bechir Hamdaoui

Publications and source records attributed to Bechir Hamdaoui.

At least 37 records · Page 2Linked to original sources

arXiv2022

Deep-Learning-Based Device Fingerprinting for Increased LoRa-IoT Security: Sensitivity to Network Deployment Changes

Deep-learning-based device fingerprinting has recently been recognized as a key enabler for automated network access authentication. Its robustness to impersonation attacks due to the inherent difficulty of replicating physical features is what distinguishes it from conventional cryptographic solutions. Although device fingerprinting has shown promising performances, its sensitivity to changes in the network operating environment still poses a major limitation. This paper presents an experimental framework that aims to study and overcome the sensitivity of LoRa-enabled device fingerprinting to such changes. We first begin by describing RF datasets we collected using our LoRa-enabled wireless device testbed. We then propose a new fingerprinting technique that exploits out-of-band distortion information caused by hardware impairments to increase the fingerprinting accuracy. Finally, we experimentally study and analyze the sensitivity of LoRa RF fingerprinting to various network setting changes. Our results show that fingerprinting does relatively well when the learning models are trained and tested under the same settings. However, when trained and tested under different settings, these models exhibit moderate sensitivity to channel condition changes and severe sensitivity to protocol configuration and receiver hardware changes when IQ data is used as input. However, with FFT data is used as input, they perform poorly under any change.

cs.LG↗

arXiv2022

An Analysis of Complex-Valued CNNs for RF Data-Driven Wireless Device Classification

Recent deep neural network-based device classification studies show that complex-valued neural networks (CVNNs) yield higher classification accuracy than real-valued neural networks (RVNNs). Although this improvement is (intuitively) attributed to the complex nature of the input RF data (i.e., IQ symbols), no prior work has taken a closer look into analyzing such a trend in the context of wireless device identification. Our study provides a deeper understanding of this trend using real LoRa and WiFi RF datasets. We perform a deep dive into understanding the impact of (i) the input representation/type and (ii) the architectural layer of the neural network. For the input representation, we considered the IQ as well as the polar coordinates both partially and fully. For the architectural layer, we considered a series of ablation experiments that eliminate parts of the CVNN components. Our results show that CVNNs consistently outperform RVNNs counterpart in the various scenarios mentioned above, indicating that CVNNs are able to make better use of the joint information provided via the in-phase (I) and quadrature (Q) components of the signal.

cs.LG↗

arXiv2022

Comprehensive RF Dataset Collection and Release: A Deep Learning-Based Device Fingerprinting Use Case

Deep learning-based RF fingerprinting has recently been recognized as a potential solution for enabling newly emerging wireless network applications, such as spectrum access policy enforcement, automated network device authentication, and unauthorized network access monitoring and control. Real, comprehensive RF datasets are now needed more than ever to enable the study, assessment, and validation of newly developed RF fingerprinting approaches. In this paper, we present and release a large-scale RF fingerprinting dataset, collected from 25 different LoRa-enabled IoT transmitting devices using USRP B210 receivers. Our dataset consists of a large number of SigMF-compliant binary files representing the I/Q time-domain samples and their corresponding FFT-based files of LoRa transmissions. This dataset provides a comprehensive set of essential experimental scenarios, considering both indoor and outdoor environments and various network deployments and configurations, such as the distance between the transmitters and the receiver, the configuration of the considered LoRa modulation, the physical location of the conducted experiment, and the receiver hardware used for training and testing the neural network models.

eess.SP↗

arXiv2021

Leveraging Multiple Transmissions and Receptions for Channel-Agnostic Deep Learning-Based Network Device Classification

The accurate identification of wireless devices is critical for enabling automated network access monitoring and authenticated data communication in large-scale networks; e.g., IoT. RF fingerprinting has emerged as a solution for device identification by leveraging the transmitter unique manufacturing impairments. Although deep learning is proven efficient in classifying devices based on the hardware impairments fingerprints, DL models perform poorly due to channel variations. That is, although training and testing neural networks using data generated during the same period achieve reliable classification, testing them on data generated at different times degrades the accuracy substantially, an already well recognized problem within the community. To the best of our knowledge, we are the first to propose to leverage MIMO capabilities to mitigate the channel effect and provide a channel-resilient device classification. We show that for AWGN channels, combining multiple received signals improves the testing accuracy by up to $30\%$. We also show that for Rayleigh channels, blind channel estimation enabled by MIMO increases the testing accuracy by up to $40\%$ when the models are trained and tested over the same channel, and by up to $60\%$ when the models are tested on a channel that is different from that used for training.

eess.SP↗

arXiv2021

Deep Neural Network Feature Designs for RF Data-Driven Wireless Device Classification

Most prior works on deep learning-based wireless device classification using radio frequency (RF) data apply off-the-shelf deep neural network (DNN) models, which were matured mainly for domains like vision and language. However, wireless RF data possesses unique characteristics that differentiate it from these other domains. For instance, RF data encompasses intermingled time and frequency features that are dictated by the underlying hardware and protocol configurations. In addition, wireless RF communication signals exhibit cyclostationarity due to repeated patterns (PHY pilots, frame prefixes, etc.) that these signals inherently contain. In this paper, we begin by explaining and showing the unsuitability as well as limitations of existing DNN feature design approaches currently proposed to be used for wireless device classification. We then present novel feature design approaches that exploit the distinct structures of the RF communication signals and the spectrum emissions caused by transmitter hardware impairments to custom-make DNN models suitable for classifying wireless devices using RF signal data. Our proposed DNN feature designs substantially improve classification robustness in terms of scalability, accuracy, signature anti-cloning, and insensitivity to environment perturbations. We end the paper by presenting other feature design strategies that have great potentials for providing further performance improvements of the DNN-based wireless device classification, and discuss the open research challenges related to these proposed strategies.

eess.SP↗

arXiv2020

Traffic Behavior in Cloud Data Centers: A Survey

Data centers (DCs) nowadays house tens of thousands of servers and switches, interconnected by high-speed communication links. With the rapid growth of cloud DCs, in both size and number, tremendous efforts have been undertaken to efficiently design the network and manage the traffic within these DCs. However, little effort has been made toward measuring, understanding and chattelizing how the network-level traffic of these DCs behave. In this paper, we aim to present a systematic taxonomy and survey of these DC studies. Specifically, our survey first decomposes DC network traffic behavior into two main stages, namely (1) data collection methodologies and (2) research findings, and then classifies and discusses the recent research studies in each stage. Finally, the survey highlights few research challenges related to DC network traffic that require further research investigation.

cs.NI↗

arXiv2020

CAFT: Congestion-Aware Fault-Tolerant Load Balancing for Three-Tier Clos Data Centers

Production data centers operate under various workload sizes ranging from latency-sensitive mice flows to long-lived elephant flows. However, the predominant load balancing scheme in data center networks, equal-cost multi-path (ECMP), is agnostic to path conditions and performs poorly in asymmetric topologies, resulting in low throughput and high latencies. In this paper, we propose CAFT, a distributed congestion-aware fault-tolerant load balancing protocol for 3-tier data center networks. It first collects, in real time, the complete congestion information of two subsets from the set of all possible paths between any two hosts. Then, the best path congestion information from each subset is carried across the switches, during the Transport Control Protocol (TCP) connection process, to make path selection decision. Having two candidate paths improve the robustness of CAFT to asymmetries caused by link failures. Large-scale ns-3 simulations show that CAFT outperforms Expeditus in mean flow completion time (FCT) and network throughput for both symmetric and asymmetric scenarios.

cs.NI↗

arXiv2020

Bert: Scalable Source Routed Multicast for Cloud Data Centers

Traditional IP multicast routing is not suitable for cloud data center (DC) networks due to the need for supporting large numbers of groups with large group sizes. State-of-the-art DC multicast routing approaches aim to overcome the scalability issues by, for instance, taking advantage of the symmetry of DC topologies and the programmability of DC switches to compactly encode multicast group information inside packets, thereby reducing the overhead resulting from the need to store the states of flows at the network switches. However, although these scale well with the number of multicast groups, they do not do so with group sizes, and as a result, they yield substantial traffic control overhead and network congestion. In this paper, we present Bert, a scalable, source-initiated DC multicast routing approach that scales well with both the number and the size of multicast groups, and does so through clustering, by dividing the members of the multicast group into a set of clusters with each cluster employing its own forwarding rules. Compared to the state-of-the-art approach, Bert yields much lesser traffic control overhead by significantly reducing the packet header sizes and the number of extra packet transmissions, resulting from the need for compacting forwarding rules across the switches.

cs.NI↗

arXiv2020

Peak Power Shaving for Reduced Electricity Costs in Cloud Data Centers: Opportunities and Challenges

An electricity bill of a data center (DC) is determined not only by how much energy the DC consumes, but especially by how the consumed energy is spread over time during the billing cycle. More specifically, these electricity costs are essentially made up of two major charges: Energy Charge, a cost based on the amount of consumed energy (in kWh), and Peak Charge, a cost based on the maximum power (in kW) requested during the billing cycle. The latter charge component is forced to encourage DCs to balance and regulate their power demands over the billing cycle, allowing the utility company to manage congestion without increasing supply. This billing model has thus called for the development of peak power shaving approaches that reduce costs by smoothing peak power demands over the billing cycle to minimize the Peak Charge component. In this paper, we investigate peak power shaving approaches, and begin by using Google data traces to quantify and provide a real sense of how much electricity cost reduction can peak power demand shaving achieve on a Google DC cluster. We then discuss why peak power shaving is well-suited for reducing electricity costs of DCs, and describe two commonly used peak shaving approaches, namely energy storage and workload modulation. We finally identify and describe key research problems that remain unsolved and require further investigation.

cs.NI↗

arXiv2020

Dynamic Spectrum Sharing in the Age of Millimeter Wave Spectrum Access

Next-generation wireless networks are facing spectrum shortage challenges, mainly due to, among other factors, the projected massive numbers of IoT connections and the emerging bandwidth-hungry applications that such networks ought to serve. Spectrum is scarce and expensive, and therefore, it is of crucial importance to devise dynamic and flexible spectrum access policies and techniques that yield optimal usage of such a precious resource. A new trend recently being adopted as a key solution to this spectrum scarcity challenge is to exploit higher frequency bands, namely mmWave bands, that were considered impractical few years ago, but are now becoming feasible due to recent advances in electronics. Though, fortunately, spectrum regulatory bodies have responded by allowing the use of new bands in the mmWave frequencies, much work still needs to be done to benefit from such new spectra. In this paper, we discuss some key spectrum management challenges that pertain to dynamic spectrum access at the mmWave frequencies, which need to be overcome in order to promote dynamic spectrum sharing at these mmWave bands. We also propose new techniques that enable efficient dynamic spectrum sharing at the mmWave bands by addressing some of the discussed challenges, and highlight open research challenges that still need to be addressed to fully unleash the potential of dynamic spectrum sharing at mmWave bands.

cs.NI↗

arXiv2020

Leveraging Hardware-Impaired Out-of-Band Information Through Deep Neural Networks for Robust Wireless Device Classification

Wireless device classification techniques play a key role in promoting emerging wireless applications such as allowing spectrum regulatory agencies to enforce their access policies and enabling network administrators to control access and prevent impersonation attacks to their wireless networks. Leveraging spectrum distortions of transmitted RF signals, caused by transceiver hardware impairments created during manufacture and assembly stages, to provide device classification has been the focus of many recent works. These prior works essentially apply deep learning to extract features of the devices from their hardware-impaired signals and rely on feature variations across the devices to distinguish devices from one another. As technology advances, the manufacturing impairment variations across devices are becoming extremely insignificant, making these prior classification approaches inaccurate. This paper proposes a novel, deep learning-based technique that provides scalable and highly accurate classification of wireless devices, even when the devices exhibit insignificant variation across their hardware impairments and have the same hardware, protocol, and software configurations. The novelty of the proposed technique lies in leveraging both the {\em in-band} and {\em out-of-band} signal distortion information by oversampling the captured signals at the receiver and feeding IQ samples collected from the RF signals to a deep neural network for classification. Using a convolutional neural network (CNN) model, we show that our proposed technique, when applied to high-end, high-performance devices with minimally distorted hardware, doubles the device classification accuracy when compared to existing approaches.

eess.SP↗

arXiv2019

Unleashing the Power of Participatory IoT with Blockchains for Increased Safety and Situation Awareness of Smart Cities

IoT emerges as an unprecedented paradigm with great potential for changing how people interact, think and live. It is making existing Internet services feasible in ways that were previously impossible, as well as paving the way for new situation-awareness applications suitable for smart cities, such as realtime video surveillance, traffic control, and emergency management. These applications will typically rely on large numbers of IoT devices to collect and collaboratively process streamed data to enable real-time decision making. In this paper, we introduce the concept of Semantic Virtual Space (SVS), an abstraction for virtualized cloud-enabled IoT infrastructure that is commensurate with the goals and needs of these emerging smart city applications, and propose and discuss scalable architectures and mechanisms that enable and automate the deployment and management of multiple SVS instances on top of the cloud-enabled IoT infrastructure.

cs.NI↗

arXiv2019

TrustSAS: A Trustworthy Spectrum Access System for the 3.5 GHz CBRS Band

As part of its ongoing efforts to meet the increased spectrum demand, the Federal Communications Commission (FCC) has recently opened up 150 MHz in the 3.5 GHz band for shared wireless broadband use. Access and operations in this band, aka Citizens Broadband Radio Service (CBRS), will be managed by a dynamic spectrum access system (SAS) to enable seamless spectrum sharing between secondary users (SUs) and incumbent users. Despite its benefits, SAS's design requirements, as set by FCC, present privacy risks to SUs, merely because SUs are required to share sensitive operational information (e.g., location, identity, spectrum usage) with SAS to be able to learn about spectrum availability in their vicinity. In this paper, we propose TrustSAS , a trustworthy framework for SAS that synergizes state-of-the-art cryptographic techniques with blockchain technology in an innovative way to address these privacy issues while complying with FCC's regulatory design requirements. We analyze the security of our framework and evaluate its performance through analysis, simulation and experimentation. We show that TrustSAS can offer high security guarantees with reasonable overhead, making it an ideal solution for addressing SUs' privacy issues in an operational SAS environment.

cs.NI↗

arXiv2019

Location Privacy in Cognitive Radios with Multi-Server Private Information Retrieval

Spectrum database-based cognitive radio networks (CRNs) have become the de facto approach for enabling unlicensed secondary users (SUs) to identify spectrum vacancies in channels owned by licensed primary users (PUs). Despite its merits, the use of spectrum databases incurs privacy concerns for both SUs and PUs. Single-server private information retrieval (PIR) has been used as the main tool to address this problem. However, such techniques incur extremely large communication and computation overheads while offering only computational privacy. Besides, some of these PIR protocols have been broken. In this paper, we show that it is possible to achieve high efficiency and (information-theoretic) privacy for both PUs and SUs in database-driven CRN with multi-server PIR. Our key observation is that, by design, database-driven CRNs comprise multiple databases that are required, by the Federal Communications Commission, to synchronize their records. To the best of our knowledge, we are the first to exploit this observation to harness multi-server PIR technology to guarantee an optimal privacy for both SUs and PUs, thanks to the unique properties of database-driven CRN . We showed, analytically and empirically with deployments on actual cloud systems, that multi-server PIR is an ideal tool to provide efficient location privacy in database-driven CRN.

cs.NI↗

arXiv2019

Partial Relay Selection For Hybrid RF/FSO Systems with Hardware Impairments

In this paper, we investigate the performance analysis of dual hop relaying system consisting of asymmetric Radio Frequency (RF)/Free Optical Space (FSO) links. The RF channels follow a Rayleigh distribution and the optical links are subject to Gamma-Gamma fading. We also introduce impairments to our model and we suggest Partial Relay Selection (PRS) protocol with Amplify-and-Forward (AF) fixed gain relaying. The benefits of employing optical communication with RF, is to increase the system transfer rate and thus improving the system bandwidth. Many previous research attempts assuming ideal hardware (source, relays, etc.) without impairments. In fact, this assumption is still valid for low-rate systems. However, these hardware impairments can no longer be neglected for high-rate systems in order to get consistent results. Novel analytical expressions of outage probability and ergodic capacity of our model are derived taking into account ideal and non-ideal hardware cases. Furthermore, we study the dependence of the outage probability and the system capacity considering, the effect of the correlation between the outdated CSI (Channel State Information) and the current source-relay link, the number of relays, the rank of the selected relay and the average optical Signal to Noise Ratio (SNR) over weak and strong atmospheric turbulence. We also demonstrate that for a non-ideal case, the end-to-end Signal to Noise plus Distortion Ratio (SNDR) has a certain ceiling for high SNR range. However, the SNDR grows infinitely for the ideal case and the ceiling caused by impairments no longer exists. Finally, numerical and simulation results are presented.

eess.SP↗

arXiv2019

Hybrid Rayleigh and Double-Weibull over Impaired RF/FSO System with Outdated CSI

In this work, we present a global framework of a dual-hop RF/FSO system with multiple relays operating at the mode of amplify-and-forward (AF) with fixed gain. Partial relay selection (PRS) protocol with outdated channel state information (CSI) is assumed since the channels of the first hop are time-varying. The optical irradiance of the second hop are subject to the Double-Weibull model while the RF channels of the first hop experience the Rayleigh fading. The signal reception is achieved either by heterodyne or intensity modulation and direct detection (IM/DD). In addition, we introduce an aggregate model of hardware impairments to the source (S) and the relays since they are not perfect nodes. In order to quantify the impairment impact on the system, we derive closed-form, approximate, upper bound and high signal-to-noise ratio (SNR) asymptotic of the outage probability (OP) and the ergodic capacity (EC). Finally, analytical and numerical results are in agreement using Monte Carlo simulation.

eess.SP↗

arXiv2019

Aggregate Hardware Impairments Over Mixed RF/FSO Relaying Systems With Outdated CSI

In this paper, we propose a dual-hop RF (Radio-Frequency)/FSO (Free-Space Optical) system with multiple relays employing the Decode-and-Forward (DF) and Amplify-and-Forward (AF) with a Fixed Gain (FG) relaying scheme. The RF channels are subject to a Rayleigh distribution while the optical links experience a unified fading model emcopassing the atmospheric turbulence that follows the Málaga distribution (or also called the $\mathcal{M}$-distribution), the atmospheric path loss and the pointing error. Partial relay selection (PRS) with outdated channel state information (CSI) is proposed to select the candidate relay to forward the signal to the destination. At the reception, the detection of the signal can be achieved following either heterodyne or Intensity Modulation and Direct Detection (IM/DD). Many previous attempts neglected the impact of the hardware impairments and assumed ideal hardware. This assumption makes sense for low data rate systems but it would no longer be valid for high data rate systems. In this work, we propose a general model of hardware impairment to get insight into quantifying its effects on the system performance. We will demonstrate that the hardware impairments have small impact on the system performance for low signal-to-noise ratio (SNR), but it can be destructive at high SNR values. Furthermore analytical expressions and upper bounds are derived for the outage probability and ergodic capacity while the symbol error probability is obtained through the numerical integration method. Capitalizing on these metrics, we also derive the high SNR asymptotes to get valuable insight into the system gains such as the diversity and the coding gains. Finally, analytical and numerical results are presented and validated by Monte Carlo simulation.

eess.SP↗

arXiv2019

Mixed RF/FSO Relaying Systems with Hardware Impairments

In this work, we provide a detailed analysis of a dual-hop fixed gain (FG) amplify-and-forward relaying system, consisting of a hybrid radio frequency (RF) and free-space optical (FSO) channels. We introduce an impairment model which is the soft envelope limiter (SEL). Additionally, we propose the partial relay selection (PRS) protocol with outdated channel state information (CSI) based on the knowledge of the RF channels in order to select one relay for the communication. Moreover, the RF channels of the first hop experience Rayleigh fading while we propose a unified fading model for the FSO channels, called the unified Gamma Gamma (GG), taking into account the atmospheric turbulence, the path loss and the misalignment between the transmitter and the receiver aperture also called the pointing error. Novel closed-forms of the outage probability (OP), the bit error probability (BEP) and the average ergodic capacity (EC) are derived in terms of Meijer-G and Fox-H functions. Capitalizing on these metrics, we also derive the asymptotical high signal-to-noise ratio (SNR) in order to get engineering insights into the impacts of the hardware impairments and the system parameters as well. Finally, using Monte Carlo simulations, we validate numerically the derived mathematical formulations.

eess.SP↗