Sorry, you need to enable JavaScript to visit this website.
Partager

Publications

 

Les publications de nos enseignants-chercheurs sont sur la plateforme HAL :

 

Les publications des thèses des docteurs du LTCI sont sur la plateforme HAL :

 

Retrouver les publications figurant dans l'archive ouverte HAL par année :

2021

  • Sparse Realization in Unreliable Spin-Transfer-Torque RAM for Convolutional Neural Network
    • Cai Hao
    • Chen Juntong
    • Zhou Yongliang
    • Hong Xiaofeng
    • Liu Bo
    • Naviner Lirida
    IEEE Transactions on Magnetics, Institute of Electrical and Electronics Engineers, 2021, 57 (2), pp.1-5. The explosive growth of in-memory computing and neural network requires stringent demands on the computational energy efficiency. Nonvolatile memories such as magnetic random access memory (MRAM) provides alternative memory solutions toward energy efficiency. Sparsity realization across emerging device, hybrid circuit, and algorithmic becomes a recent trend in neural network. Previous sparse adaption in memories mainly focused on high level analysis. In this article, the sparse realization of hybrid magnetic/CMOS integration is first proposed for convolutional neural network (CNN). Simulation results with representative data sets CIFAR-10 show that MRAM sensing operation can be speedup 6.4× with 84.46% sparsity. The proposed training and retraining phases can solve unreliable sensing issues with a proper sparsity selection. (10.1109/TMAG.2020.3015146)
    DOI : 10.1109/TMAG.2020.3015146
  • Security Analysis of Out-of-Band Device Pairing Protocols: A Survey
    • Khalfaoui Sameh
    • Leneutre Jean
    • Villard Arthur
    • Ma Jingxuan
    • Urien Pascal
    Wireless Communications and Mobile Computing, Hindawi Publishing Corporation, 2021, 2021, pp.1-30. Numerous secure device pairing (SDP) protocols have been proposed to establish a secure communication between unidentified IoT devices that have no preshared security parameters due to the scalability requirements imposed by the ubiquitous nature of the IoT devices. In order to provide the most user-friendly IoT services, the usability assessment has become the main requirement. Thus, the complete security analysis has been replaced by a sketch of a proof to partially validate the robustness of the proposal. The few existing formal or computational security verifications on the SDP schemes have been conducted based on the assessment of a wide variety of uniquely defined security properties. Therefore, the security comparison between these protocols is not feasible and there is a lack of a unified security analysis framework to assess these pairing techniques. In this paper, we survey a selection of secure device pairing proposals that have been formally or computationally verified. We present a systematic description of the protocol assumptions, the adopted verification model, and an assessment of the verification results. In addition, we normalize the used taxonomy in order to enhance the understanding of these security validations. Furthermore, we refine the adversary capabilities on the out-of-band channel by redefining the replay capability and by introducing a new notion of delay that is dependent on the protocol structure that is more adequate for the ad hoc pairing context. Also, we propose a classification of a number of out-of-band channels based on their security properties and under our refined adversary model. Our work motivates the future SDP protocol designer to conduct a formal or a computational security assessment to allow the comparability between these pairing techniques. Furthermore, it provides a realistic abstraction of the adversary capabilities on the out-of-band channel which improves the modeling of their security characteristics in the protocol verification tools. (10.1155/2021/8887472)
    DOI : 10.1155/2021/8887472
  • Energy modeling of Hoeffding tree ensembles
    • García-Martín Eva
    • Bifet Albert
    • Lavesson Niklas
    Intelligent Data Analysis, IOS Press, 2021, 25 (1), pp.81--104. Energy consumption reduction has been an increasing trend in machine learning over the past few years due to its socio-ecological importance. In new challenging areas such as edge computing, energy consumption and predictive accuracy are key variables during algorithm design and implementation. State-of-the-art ensemble stream mining algorithms are able to create highly accurate predictions at a substantial energy cost. This paper introduces the nmin adaptation method to ensembles of Hoeffding tree algorithms, to further reduce their energy consumption without sacrificing accuracy. We also present extensive theoretical energy models of such algorithms, detailing their energy patterns and how nmin adaptation affects their energy consumption. We have evaluated the energy efficiency and accuracy of the nmin adaptation method on five different ensembles of Hoeffding trees under 11 publicly available datasets. The results show that we are able to reduce the energy consumption significantly, by 21% on average, affecting accuracy by less than one percent on average. (10.3233/IDA-194890)
    DOI : 10.3233/IDA-194890
  • Efficient scheduling of applications onto cloud FPGAs
    • Bertolino Matteo
    , 2021. This thesis has been realized in Télécom Paris and it has been financed by Nokia Bell Labs France. It founds its motivations in the increasing usage of hardware accelerators such as FPGAs and their recent integration in modern cloud data center [1][2]. In some cases, servers and FPGAs are rented to users and the cost is related to the utilization time. Thus, offering a better sharing of FPGA pools would interest all stakeholders, namely cloud providers and users. We focus on scheduling and, in particular, we focus on makespan minimization of applications. The latter are assumed to be composed of several dependent tasks, whose features (i.e., dependencies, execution time, resource requirements, and so on) are known prior to their execution. With respect to the state of the art, we have sought to design an approach which is, at the same time, (i) general, (ii) fast and (iii) of high-quality. Indeed, several related works represent the applications and the architecture through simple models (e.g., the FPGA is often represented only with the amount of reconfigurable logic). We retain that such simple models may lead to unfeasible scheduling. Moreover, the vast majority of them is either based on slow and precise algorithms or on fast heuristics whose quality is far from the optimum. We therefore propose a scheduling solution [3] characterized by a good quality in terms of makespan while keeping the decision time in the order of tens of milliseconds for common applications. The main contributions of the thesis are a modelling proposal for FPGAs, the design of a heuristic which targets the makespan minimization and the evaluation of this heuristic on a synthetic benchmark of pseudo-randomly generated applications. Additionally, we have integrated this method to a model-driven engineering (MDE) tool to better support the early design of embedded systems. Finally, we propose several extensions to extend the approach to different architectures.References:[1] A. M. Caulfield et al., "A cloud-scale acceleration architecture," 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), Taipei, 2016, pp. 1-13, doi: 10.1109/MICRO.2016.7783710[2] Amazon Web Services Elastic Compute Cloud, https://docs.aws.amazon.com/ec2/index.html?nc2=h_ql_doc_ec2[3] Matteo Bertolino, Andrea Enrici, Renaud Pacalet, Ludovic Apvrille. Efficient Scheduling of FPGAs for Cloud Data Center Infrastructures. Euromicro DSD 2020, Aug 2020, Portorož, Slovenia. Proceedings will be published on IEEExplore, paper available on HAL of Télécom Paris: https://hal.telecom-paris.fr/hal-02894662v1
  • Heavy-tailed nature of stochastic gradient descent in deep learning : theoretical and empirical analysis
    • Nguyen Thanh Huy
    , 2021. In this thesis, we are concerned with the Stochastic Gradient Descent (SGD) algorithm. Specifically, we perform theoretical and empirical analysis of the behavior of the stochastic gradient noise (GN), which is defined as the difference between the true gradient and the stochastic gradient, in deep neural networks. Based on these results, we bring an alternative perspective to the existing approaches for investigating SGD. The GN in SGD is often considered to be Gaussian for mathematical convenience. This assumption enables SGD to be studied as a stochastic differential equation (SDE) driven by a Brownian motion. We argue that the Gaussianity assumption might fail to hold in deep learning settings and hence render the Brownian motion-based analyses inappropriate. Inspired by non-Gaussian natural phenomena, we consider the GN in a more general context that suggests that the GN is better approximated by a "heavy-tailed" alpha-stable random vector. Accordingly, we propose to analyze SGD as a discretization of an SDE driven by a Lévy motion. Firstly, to justify the alpha-stable assumption, we conduct experiments on common deep learning scenarios and show that in all settings, the GN is highly non-Gaussian and exhibits heavy-tails. Secondly, under the heavy-tailed GN assumption, we provide a non-asymptotic analysis for the discrete-time dynamics SGD to converge to the global minimum in terms of suboptimality. Finally, we investigate the metastability nature of the SDE driven by Lévy motion that can then be exploited for clarifying the behavior of SGD, especially in terms of `preferring wide minima'. More precisely, we provide formal theoretical analysis where we derive explicit conditions for the step-size such that the metastability behavior of SGD, viewed as a discrete-time SDE, is similar to its continuous-time limit. We show that the behaviors of the two systems are indeed similar for small step-sizes and we describe how the error depends on the algorithm and problem parameters. We illustrate our metastability results with simulations on a synthetic model and neural networks. Our results open up a different perspective and shed more light on the view that SGD prefers wide minima.
  • Comparing Representations for Audio Synthesis Using Generative Adversarial Networks
    • Richard Gaël
    • Nistal Javier
    • Plattner Stefan
    , 2021, pp.161-165. —In this paper, we compare different audio signal representations, including the raw audio waveform and a variety of time-frequency representations, for the task of audio synthesis with Generative Adversarial Networks (GANs). We conduct the experiments on a subset of the NSynth dataset. The architecture follows the benchmark Progressive Growing Wasserstein GAN. We perform experiments both in a fully non-conditional manner as well as conditioning the network on the pitch information. We quantitatively evaluate the generated material utilizing standard metrics for assessing generative models, and compare training and sampling times. We show that complex-valued as well as the magnitude and Instantaneous Frequency of the ShortTime Fourier Transform achieve the best results, and yield fast generation and inversion times. The code for feature extraction, training and evaluating the model is available online. (10.23919/Eusipco47968.2020.9287799)
    DOI : 10.23919/Eusipco47968.2020.9287799
  • Multi-Domain Image-to-Image Translation with Adaptive Inference Graph
    • Nguyen The-Phuc
    • Lathuilière Stéphane
    • Ricci Elisa
    , 2021. In this work, we address the problem of multi-domain image-to-image translation with particular attention paid to computational cost. In particular, current state of the art models require a large and deep model in order to handle the visual diversity of multiple domains. In a context of limited computational resources, increasing the network size may not be possible. Therefore, we propose to increase the network capacity by using an adaptive graph structure. At inference time, the network estimates its own graph by selecting specific sub-networks. Sub-network selection is implemented using Gumbel-Softmax in order to allow end-to-end training. This approach leads to an adjustable increase in number of parameters while preserving an almost constant computational cost. Our evaluation on two publicly available datasets of facial and painting images shows that our adaptive strategy generates better images with fewer artifacts than literature methods
  • DR2S : Deep Regression with Region Selection for Camera Quality Evaluation
    • Tworski Marcelin
    • Lathuilière Stéphane
    • Belkarfa Salim
    • Fiandrotti Attilio
    • Cagnazzo Marco
    , 2020. In this work, we tackle the problem of estimating a camera capability to preserve fine texture details at a given lighting condition. Importantly, our texture preservation measurement should coincide with human perception. Consequently, we formulate our problem as a regression one and we introduce a deep convolutional network to estimate texture quality score. At training time, we use ground-truth quality scores provided by expert human annotators in order to obtain a subjective quality measure. In addition, we propose a region selection method to identify the image regions that are better suited at measuring perceptual quality. Finally, our experimental evaluation shows that our learning-based approach outperforms existing methods and that our region selection algorithm consistently improves the quality estimation.
  • Learning Visual Voice Activity Detection with an Automatically Annotated Dataset
    • Guy Sylvain
    • Lathuilière Stéphane
    • Mesejo Pablo
    • Horaud Radu
    , 2021, pp.4851-4856. Visual voice activity detection (V-VAD) uses visual features to predict whether a person is speaking or not. VVAD is useful whenever audio VAD (A-VAD) is inefficient either because the acoustic signal is difficult to analyze or because it is simply missing. We propose two deep architectures for V-VAD, one based on facial landmarks and one based on optical flow. Moreover, available datasets, used for learning and for testing VVAD, lack content variability. We introduce a novel methodology to automatically create and annotate very large datasets inthe-wild – WildVVAD – based on combining A-VAD with face detection and tracking. A thorough empirical evaluation showsthe advantage of training the proposed deep V-VAD models with this dataset. (10.1109/ICPR48806.2021.9412884)
    DOI : 10.1109/ICPR48806.2021.9412884
  • CARRADA Dataset: Camera and Automotive Radar with Range-Angle-Doppler Annotations
    • Ouaknine Arthur
    • Newson Alasdair
    • Rebut Julien
    • Tupin Florence
    • Perez Patrick
    2020 25th International Conference on Pattern Recognition (ICPR), 2021. High quality perception is essential for autonomous driving (AD) systems. To reach the accuracy and robustness that are required by such systems, several types of sensors must be combined. Currently, mostly cameras and laser scanners (lidar) are deployed to build a representation of the world around the vehicle. While radar sensors have been used for a long time in the automotive industry, they are still under-used for AD despite their appealing characteristics (notably, their ability to measure the relative speed of obstacles and to operate even in adverse weather conditions). To a large extent, this situation is due to the relative lack of automotive datasets with real radar signals that are both raw and annotated. In this work, we introduce CARRADA, a dataset of synchronized camera and radar recordings with rangeangle-Doppler annotations. We also present a semi-automatic annotation approach, which was used to annotate the dataset, and a radar semantic segmentation baseline, which we evaluate on several metrics. Both our code and dataset are available online. (10.1109/icpr48806.2021.9413181)
    DOI : 10.1109/icpr48806.2021.9413181
  • CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification
    • Delorme Guillaume
    • Xu Yihong
    • Lathuilière Stéphane
    • Horaud Radu
    • Alameda-Pineda Xavier
    , 2021, pp.4428-4435. Unsupervised person re-ID is the task of identifying people on a target data set for which the ID labels are unavailable during training. In this paper, we propose to unify two trends in unsupervised person re-ID: clustering & fine-tuning and adversarial learning. On one side, clustering groups training images into pseudo-ID labels, and uses them to fine-tune the feature extractor. On the other side, adversarial learning is used, inspired by domain adaptation, to match distributions from different domains. Since target data is distributed across different camera viewpoints, we propose to model each camera as an independent domain, and aim to learn domain-independent features. Straightforward adversarial learning yields negative transfer, we thus introduce a conditioning vector to mitigate this undesirable effect. In our framework, the centroid of the cluster to which the visual sample belongs is used as conditioning vector of our conditional adversarial network, where the vector is permutation invariant (clusters ordering does not matter) and its size is independent of the number of clusters. To our knowledge, we are the first to propose the use of conditional adversar-ial networks for unsupervised person re-ID. We evaluate the proposed architecture on top of two state-of-the-art clustering-based unsupervised person re-identification (re-ID) methods on four different experimental settings with three different data sets and set the new state-of-the-art performance on all four of them. Our code and model will be made publicly available at https://team.inria.fr/perception/canu-reid/. (10.1109/ICPR48806.2021.9412431)
    DOI : 10.1109/ICPR48806.2021.9412431
  • Innovative TLS 1.3 Identity Module for Trusted IoT Device
    • Urien Pascal
    , 2021, pp.1-4. (10.1109/CCNC49032.2021.9369656)
    DOI : 10.1109/CCNC49032.2021.9369656
  • A New IoT Trust Model Based on TLS-SE and TLS-IM Secure Elements: A Blockchain Use Case
    • Urien Pascal
    , 2021, pp.1-2. (10.1109/CCNC49032.2021.9369485)
    DOI : 10.1109/CCNC49032.2021.9369485
  • Machine Learning Detection for SMiShing Frauds
    • Msahli Mounira
    • Boukari Badr Eddine
    • Ravi Akshaya
    , 2021, pp.1-2. (10.1109/CCNC49032.2021.9369640)
    DOI : 10.1109/CCNC49032.2021.9369640
  • A Survey on the Current Security Landscape of Intelligent Transportation Systems
    • Lamssaggad Ayyoub
    • Benamar Nabil
    • Hafid Abdelhakim Senhaji
    • Msahli Mounira
    IEEE Access, IEEE, 2021, pp.1-1. (10.1109/ACCESS.2021.3050038)
    DOI : 10.1109/ACCESS.2021.3050038
  • Survey on Feature Transformation Techniques for Data Streams
    • Bahri Maroua
    • Bifet Albert
    • Maniu Silviu
    • Gomes Heitor Murilo
    , 2021, pp.4796-4802. Mining high-dimensional data streams poses a fundamental challenge to machine learning as the presence of high numbers of attributes can remarkably degrade any mining task’s performance. In the past several years, dimension reduction (DR) approaches have been successfully applied for different purposes (e.g., visualization). Due to their high-computational costs and numerous passes overlarge data, these approaches pose a hindrance when processing infinite data streams that are potentially high-dimensional. The latter increases the resource-usage of algorithms that could suffer from the curse of dimensionality. To cope with these issues, some techniques for incremental DR have been proposed. In this paper, we provide a survey on reduction approaches designed to handle data streams and highlight the key benefits of using these approaches for stream mining algorithms. (10.24963/ijcai.2020/668)
    DOI : 10.24963/ijcai.2020/668
  • Intrinsic Resiliency of S-boxes Against Side-Channel Attacks -Best And Worst Scenarios
    • Carlet Claude
    • de Chérisey Eloi
    • Guilley Sylvain
    • Kavut Selçuk
    • Tang Deng
    IEEE Transactions on Information Forensics and Security, Institute of Electrical and Electronics Engineers, 2021, 16, pp.203-218. Constructing S-boxes that are inherently resistant against side-channel attacks is an important problem in cryptography. By using an optimal distinguisher under an additive Gaussian noise assumption, we clarify how a defender (resp., an attacker) can make side-channel attacks as difficult (resp., easy) as possible, in relation with the auto-correlation spectrum of Boolean functions. We then construct balanced Boolean functions that are optimal for each of these two scenarios. Generalizing the objectives for an S-box, we analyze the auto-correlation spectra of some well-known S-box constructions in dimensions at most 8 and compare their intrinsic resiliency against side-channel attacks. Finally, we perform several simulations of side-channel attacks against the aforementioned constructions, which confirm our theoretical approach. (10.1109/TIFS.2020.3006399)
    DOI : 10.1109/TIFS.2020.3006399
  • Solving analogies on words based on minimal complexity transformation
    • Murena Pierre Alexandre
    • Al-Ghossein Marie
    • Dessalles Jean-Louis
    • Cornuéjols Antoine
    , 2020, pp.1848-1854. Analogies are 4-ary relations of the form “A is to B as C is to D”. When A, B and C are fixed, we call analogical equation the problem of finding the correct D. A direct applicative domain is Natural Language Processing, in which it has been shown successful on word inflections, such as conjugation or declension. If most approaches rely on the axioms of proportional analogy to solve these equations, these axioms are known to have limitations, in particular in the nature of the considered flections. In this paper, we propose an alternative approach, based on the assumption that optimal word inflections are transformations of minimal complexity. We propose a rough estimation of complexity for word analogies and an algorithm to find the optimal transformations. We illustrate our method on a large-scale benchmark dataset and compare with state-of-the-art approaches to demonstrate the interest of using complexity to solve analogies on words.
  • Scalable Semidefinite Programming
    • Yurtsever Alp
    • Tropp Joel A.
    • Fercoq Olivier
    • Udell Madeleine
    • Cevher Volkan
    SIAM Journal on Mathematics of Data Science, Society for Industrial and Applied Mathematics, 2021. Semidefinite programming (SDP) is a powerful framework from convex optimization that has striking potential for data science applications. This paper develops a provably correct algorithm for solving large SDP problems by economizing on both the storage and the arithmetic costs. Numerical evidence shows that the method is effective for a range of applications, including relaxations of MaxCut, abstract phase retrieval, and quadratic assignment. Running on a laptop, the algorithm can handle SDP instances where the matrix variable has over $10^{13}$ entries. (10.1137/19M1305045)
    DOI : 10.1137/19M1305045
  • Narrow River Extraction from SAR Images Using Exogenous Information
    • Gasnier Nicolas
    • Denis Loïc
    • Fjørtoft Roger
    • Liege Frédéric
    • Tupin Florence
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, IEEE, 2021, 14, pp.5720 - 5734. Monitoring of rivers is of major scientific and societal importance due to the crucial resource they provide to human activities and the threats caused by flood events. Rapid revisit synthetic aperture radar (SAR) sensors such as Sentinel-1 or the future surface water and ocean topography (SWOT) mission are indispensable tools to achieve all-weather monitoring of water bodies at the global scale. Unfortunately, at the spatial resolution of these sensors, the extraction of narrow rivers is extremely difficult without resorting to exogenous knowledge. This article introduces an innovative river segmentation method from SAR images using a priori databases such as the global river widths from Landsat (GRWL). First, a recently proposed linear structure detector is used to produce a map of likely line structures. Then, a limited number of nodes along the prior river centerline are extracted from the exogenous database and used to reconstruct the full river centerline from the detection map. Finally, an innovative conditional random field approach is used to delineate accurately the river extent around its centerline. The proposed method has been tested on several Sentinel-1 images and on simulated SWOT data. Both visual and qualitative evaluations demonstrate its efficiency. (10.1109/JSTARS.2021.3083413)
    DOI : 10.1109/JSTARS.2021.3083413
  • Deep Learning for Audio and Music
    • Peeters Geoffroy
    • Richard Gael
    , 2021.
  • On the use and denoising of the temporal geometric mean for SAR time series
    • Gasnier Nicolas
    • Denis Loïc
    • Tupin Florence
    IEEE Geoscience and Remote Sensing Letters, IEEE - Institute of Electrical and Electronics Engineers, 2021. The increasing availability of SAR time series creates many opportunities for remote sensing applications, but it can be challenging in terms of amount of data to process. This letter discusses the interest of the geometric mean to average SAR time series. First, the properties of the geometric mean and of the arithmetic mean are compared. Then, a speckle-reduction method specifically designed to improve images obtained with the geometric mean is presented. This method is based on an adaptation of the MuLoG framework to take into account the specific distribution of the geometric mean. Finally, applications of this denoised geometric-mean image are presented. (10.1109/LGRS.2021.3051936)
    DOI : 10.1109/LGRS.2021.3051936
  • Attention-Based Neural Network Equalization in Fiber-Optic Communications
    • Shahkarami Abtin
    • Yousefi Mansoor
    • Jaouën Yves
    Asia Communications and Photonics Conference 2021, 2021. An attention mechanism is integrated into neural network-based equalizers to prune the fully-connected output layer. For a 100 GBd 16-QAM 20 × 100 km SMF transmission, this approach reduces the computational complexity by ∼15% in a CNN+LSTM model. (10.1364/acpc.2021.m5h.3)
    DOI : 10.1364/acpc.2021.m5h.3
  • Free-space video broadcasting with a packaged, air-cooled, mid-infrared quantum cascade laser
    • Didier Pierre
    • Spitz Olivier
    • Grillot Frédéric
    , 2021.
  • Data Physicalization: Introduction to the Special Issue on Data Physicalization (part 2)
    • Hogan Trevor
    • Hinrichs Uta
    • Huron Samuel
    • Alexander Jason
    • Jansen Yvonne
    IEEE Computer Graphics and Applications, Institute of Electrical and Electronics Engineers, 2021, 41 (1), pp.63-64. (10.1109/MCG.2020.3043983)
    DOI : 10.1109/MCG.2020.3043983