Publications

2021

• Virtual Platform to Analyze the Security of a System on Chip at Microarchitectural Level
  
  • Forcioli Quentin
  • Danger Jean-Luc
  • Maurice Clémentine
  • Bossuet Lilian
  • Bruguier Florent
  • Mushtaq Maria
  • Novo David
  • France Loïc
  • Benoit Pascal
  • Guilley Sylvain
  • Perianin Thomas
  , 2021, pp.96-102. The processors (CPUs) embedded in System on Chip (SoC) have to face recent attacks taking advantage of vulnerabilities/features in their microarchitectures to retrieve secret information. Indeed, the increase in complexity of modern CPU and SoC is mainly driven by the seek of performance rather than security. Even if efforts like isolation techniques have been taken to thwart cyberattacks, most microarchitectural features can open the door to security holes. One typical example is the exploitation of cache memory which keeps track of the program execution and paves the way to side-channel (SCA) analysis and transient execution attacks like Meltdown and Spectre, which take advantage of speculative execution. This paper introduces an ongoing study aiming at analyzing the attacks relying on the hardware vulnerabilities of the microarchitectures of CPUs and SoCs. The main objective is to create a virtual and open platform that simulates the behavior of microarchitectural features and their interactions with the peripherals, like accelerators and memories in emerging technologies. The gem5 simulator, whose configuration can be customized to a specific CPU or SoC architecture, is the basis of our chosen platform for security analysis. (10.1109/EuroSPW54576.2021.00017)
  DOI : 10.1109/EuroSPW54576.2021.00017
• Language-Independent Bimodal System for Early Parkinson’s Disease Detection
  
  • Taleb Catherine
  • Likforman-Sulem Laurence
  • Mokbel Chafic
  , 2021, 12823, pp.397-413. Parkinson’s disease (PD) is a complex disorder characterized by several motor and non-motor symptoms that worsen over time, and that differ from person to another. In the early stages, when the symptoms are often incomplete, the diagnosis becomes difficult and at times, the subject may remain undiagnosed. This difficulty is a strong motivation for computer-based assessment tools that can aid in the early diagnosing and predicting the progression of PD. Handwriting’s deterioration, vocal and eye movement impairments may be ones of the earliest indicators for the onset of the illness. A language independent model to detect PD at early stages by using multimodal signals has not been enough addressed. Due to the lack of multimodal and multilingual databases, database which includes online handwriting, speech signals, and eye movement’s recordings have been recently collected. After succeeding in building language independent models for PD early diagnosis using pure handwriting or speech, we propose in this work language independent models based on bimodal analyses (handwriting and speech), where both SVM and deep learning models are studied. Our experiments show that classification accuracy up to 100% can be obtained by our SVM model through handwriting/speech bimodal analysis (10.1007/978-3-030-86334-0_26)
  DOI : 10.1007/978-3-030-86334-0_26
• CURIE: a cellular automaton for concept drift detection
  
  • Lobo Jesus L.
  • Ser Javier Del
  • Osaba Eneko
  • Bifet Albert
  • Herrera Francisco
  Data Mining and Knowledge Discovery, Springer, 2021, 35 (6), pp.2655--2678. Data stream mining extracts information from large quantities of data flowing fast and continuously (data streams). They are usually affected by changes in the data distribution, giving rise to a phenomenon referred to as concept drift. Thus, learning models must detect and adapt to such changes, so as to exhibit a good predictive performance after a drift has occurred. In this regard, the development of effective drift detection algorithms becomes a key factor in data stream mining. In this work we propose CURIE, a drift detector relying on cellular automata. Specifically, in CURIE the distribution of the data stream is represented in the grid of a cellular automata, whose neighborhood rule can then be utilized to detect possible distribution changes over the stream. Computer simulations are presented and discussed to show that CURIE, when hybridized with other base learners, renders a competitive behavior in terms of detection metrics and classification accuracy. CURIE is compared with well-established drift detectors over synthetic datasets with varying drift characteristics. (10.1007/S10618-021-00776-2)
  DOI : 10.1007/S10618-021-00776-2
• Optimal Concurrency for List-Based Sets
  
  • Kuznetsov Petr
  • Aksenov Vitaly
  • Gramoli Vincent
  • Ravi Srivatsan
  , 2021.
• Litmus-RT plugins for global static scheduling of mixed criticality systems
  
  • Pautet Laurent
  • Robert Thomas
  • Tardieu Samuel
  Journal of Systems Architecture, Elsevier, 2021, 118, pp.102221. Global static scheduling for Mixed Criticality (MC) systems demonstrates excellent results in terms of acceptance ratio and number of preemptions. But, no practical implementation and empirical evaluation have been presented yet for multi-processors systems. Moreover, the new kernel mechanisms it would require have not been studied. In this paper, we present two contributions on the implementation of global static schedulers For MC systems: G-RES, a global table-driven reservations LITMUS RT plugin, and G-MCRES, another LITMUS RT plugin scheduling MC tasks with global table-driven reservations and enforcing safe criticality mode changes. These contributions aim to solve the problems of instantaneous migrations and simultaneous mode changes in the context of global static schedulers. We based our experiments on scheduling tables generated off-line by GMH-MC-DAG, a meta-heuristic to schedule multiprocessor systems composed of multi-periodic Directed Acyclic Graphs of Mixed Criticality tasks with multiple criticality levels. The performances are very good w.r.t those of LITMUS RT and consistent with our temporal complexity evaluations. (10.1016/j.sysarc.2021.102221)
  DOI : 10.1016/j.sysarc.2021.102221
• Changer d'aire
  
  • Zayana Karim
  • Boyer Ivan
  • Rabiet Victor
  CultureMath, ENS, 2021. Le changement de variable pour les intégrales doubles en image
• Analysis and simulation of the relative intensity noise in a Fabry-Perot interband cascade laser highlight relaxation oscillations in the GHz range
  
  • Didier Pierre
  • Spitz O
  • Diaz-Thomas D A
  • Baranov A N
  • Cerutti Laurent
  • Grillot F
  , 2021.
• Capacity-Achieving Input Distribution in Per-Sample Zero-Dispersion Model of Optical Fiber
  
  • Fahs Jihad
  • Tchamkerten Aslan
  • Yousefi Mansoor
  IEEE Transactions on Information Theory, Institute of Electrical and Electronics Engineers, 2021, 67 (9), pp.5840-5852. The per-sample zero-dispersion channel model of the optical fiber is considered. It is shown that capacity is uniquely achieved by an input probability distribution that has continuous uniform phase and discrete amplitude that takes on finitely many values. This result holds when the channel is subject to general input cost constraints, that include a peak amplitude constraint and a joint average and peak amplitude constraint. (10.1109/TIT.2021.3095411)
  DOI : 10.1109/TIT.2021.3095411
• Analysis of a Laser-induced Instructions Replay Fault Model in a 32-bit Microcontroller
  
  • Khuat Vanthanh
  • Dutertre Jean-Max
  • Danger Jean-Luc
  , 2021, pp.363-370. (10.1109/DSD53832.2021.00061)
  DOI : 10.1109/DSD53832.2021.00061
• RSM Protection of the PRESENT Lightweight Cipher as a RISC-V Extension
  
  • Tehrani Etienne
  • Graba Tarik
  • Si Merabet Abdelmalek
  • Danger Jean-Luc
  , 2021, pp.325-332. (10.1109/DSD53832.2021.00056)
  DOI : 10.1109/DSD53832.2021.00056
• Hybrid dual stream blender for wide baseline view synthesis
  
  • Hobloss Nour
  • Zhang Lu
  • Lathuiliere Stephane
  • Cagnazzo Marco
  • Fiandrotti Attilio
  Signal Processing: Image Communication, Elsevier, 2021, 97, pp.116366. Free navigation of a scene requires warping some reference views to some desired target viewpoint and blending them to synthesize a virtual view. Convolutional Neural Networks (ConvNets) based methods can learn both the warping and blending tasks jointly. Such methods are often designed for moderate inter-camera baseline distance and larger kernels are required for warping if the baseline distance increases. Algorithmic methods can in principle deal with large baselines, however the synthesized view suffers from artifacts near disoccluded pixels. We present a hybrid approach where first, reference views are algorithmically warped to the target position and then are blended via a ConvNet. Preliminary view warping allows reducing the size of the convolutional kernels and thus the learnable parameters count. We propose a residual encoder-decoder for image blending with a Siamese encoder to further keep the parameters count low. We also contribute a hole inpainting algorithm to fill the disocclusions in the warped views. Our view synthesis experiments on real multiview sequences show better objective image quality than state-of-the-art methods due to fewer artifacts in the synthesized images. (10.1016/j.image.2021.116366)
  DOI : 10.1016/j.image.2021.116366
• Machine learning algorithms for dynamic Internet of Things
  
  • Boulegane Dihia
  , 2021. With the rapid growth of Internet-of-Things (IoT) devices and sensors, sources that are continuously releasing and curating vast amount of data at high pace in the form of stream. The ubiquitous data streams are essential for data driven decisionmaking in different business sectors using Artificial Intelligence (AI) and Machine Learning (ML) techniques in order to extract valuable knowledge and turn it to appropriate actions. Besides, the data being collected is often associated with a temporal indicator, referred to as temporal data stream that is a potentially infinite sequence of observations captured over time at regular intervals, but not necessarily. Forecasting is a challenging tasks in the field of AI and aims at understanding the process generating the observations over time based on past data in order to accurately predict future behavior. Stream Learning is the emerging research field which focuses on learning from infinite and evolving data streams. The thesis tackles dynamic model combination that achieves competitive results despite their high computational costs in terms of memory and time. We study several approaches to estimate the predictive performance of individual forecasting models according to the data and contribute by introducing novel windowing and meta-learning based methods to cope with evolving data streams. Subsequently, we propose different selection methods that aim at constituting a committee of accurate and diverse models. The predictions of these models are then weighted and aggregated. The second part addresses model compression that aims at building a single model to mimic the behavior of a highly performing and complex ensemble while reducing its complexity. Finally, we present the first streaming competition ”Real-time Machine Learning Competition on Data Streams”, at the IEEE Big Data 2019 conference, using the new SCALAR platform
• Investigation for 8-bit SKINNY-like S-boxes, analysis and applications
  
  • Fan Yanhong
  • Mesnager Sihem
  • Wang Weijia
  • Li Yongqing
  • Cui Tingting
  • Wang Meiqin
  Cryptography and Communications - Discrete Structures, Boolean Functions and Sequences, Springer, 2021, 13 (5), pp.617-636. (10.1007/s12095-021-00486-y)
  DOI : 10.1007/s12095-021-00486-y
• e iα + e iβ : demi-somme, carton plein !
  
  • Zayana Karim
  • Rabiet Victor
  CultureMath, ENS, 2021.
• B-OTDR Solution for Independent Temperature and Strain Measurement in a Single Acquisition
  
  • Clement Pierre
  • Gabet Renaud
  • Lanticq Vincent
  • Jaouën Yves
  Journal of Lightwave Technology, Institute of Electrical and Electronics Engineers (IEEE)/Optical Society of America(OSA), 2021, 39 (18), pp.6013-6020. (10.1109/JLT.2021.3088956)
  DOI : 10.1109/JLT.2021.3088956
• Priority-Resource-Limited JT-CoMP Scheme for Small Dense Networks
  
  • Askri Aymen
  • Rekaya-Ben Othman Ghaya
  , 2021.
• Inference of virtual network functions' state via analysis of the CPU behavior
  
  • Shelbourne Charles
  • Linguaglossa Leonardo
  • Zhang Tianzhu
  • Lipani Aldo
  , 2021.
• ObjectivAIze: Measuring Performance and Biases in Augmented Business Decision Systems
  
  • Baudel Thomas
  • Verbockhaven Manon
  • Cousergue Victoire
  • Roy Guillaume
  • Laarach Rida
  , 2021, LNCS-12934 (Part III), pp.300-320. Business process management organizes flows of information and decisions in large organizations. These systems now integrate algorithmic decision aids leveraging machine learning: each time a stakeholder needs to make a decision, such as a purchase, a quote, or hiring someone, the software leverages the inputs and outcomes of similar past decisions to provide guidance, as a recommendation. If the confidence is high, the process may be automated. Otherwise, it may still help provide consistency in the decisions. Yet, we may question how these aids affect task performance. Can we measure an improvement? Can hidden biases influence decision makers negatively? What is the impact of various presentation options? To address those issues, we propose metrics of performance, automation bias and resistance. We validated those measures with an online study. Our aim is to instrument those systems to secure their benefits. In a first experiment, we study effective collaboration. Faced with a decision, subjects alone have a success rate of 72%; Aided by a recommender that has a 75% success rate, their success rate reaches 76%. The human-system collaboration had thus a greater success rate than each taken alone. However, we noted a complacency/authority bias that degraded the quality of decisions by 5% when the recommender was wrong. This suggests that any lingering algorithmic bias may be amplified by decision aids. In a second experiment, we evaluated the effectiveness of 5 presentation variants in reducing complacency bias. We found that optional presentation increases subjects’ resistance to wrong recommendations. We intend to leverage these findings to guide the design of human-algorithm collaboration in financial compliance alert filtering. (10.1007/978-3-030-85613-7_22)
  DOI : 10.1007/978-3-030-85613-7_22
• Conditional Independence for Pretext Task Selection in Self-Supervised Speech Representation Learning
  
  • Zaiem Salah
  • Parcollet Titouan
  • Essid Slim
  , 2021, pp.2851-2855. Through solving pretext tasks, self-supervised learning (SSL) leverages unlabeled data to extract useful latent representations replacing traditional input features in the downstream task. A common pretext task consists in pretraining a SSL model on pseudo-labels derived from the original signal. This technique is particularly relevant for speech data where various meaningful signal processing features may serve as pseudolabels. However, the process of selecting pseudo-labels, for speech or other types of data, remains mostly unexplored and currently relies on observing the results on the final downstream task. Nevertheless, this methodology is not sustainable at scale due to substantial computational (hence carbon) costs. Thus, this paper introduces a practical and theoretical framework to select relevant pseudo-labels with respect to a given downstream task. More precisely, we propose a functional estimator of the pseudo-label utility grounded in the conditional independence theory, which does not require any training. The experiments conducted on speaker recognition and automatic speech recognition validate our estimator, showing a significant correlation between the performance observed on the downstream task and the utility estimates obtained with our approach, facilitating the prospection of relevant pseudo-labels for selfsupervised speech representation learning. (10.21437/interspeech.2021-1027)
  DOI : 10.21437/interspeech.2021-1027
• RF energy harvesting for LoRaWAN operation
  
  • Finnegan Joseph
  • Niotaki Kyriaki
  • Brown Stephen
  , 2021. Recently, there has been an increased interest in Low-Power Wide-Area Network (LPWAN) for the Internet of Things (IoT) applications. To overcome the battery limitations associated with the long scale IoT deployment, there has been an increased research interest in collecting energy from the environment in order to provide unlimited lifetime for these devices. There are many forms of energy that can be harvested for the selfsustainable operation of LoRa devices, such as solar and thermal energy, to name a few [1]. Here, we focus on the energy coming from the existing radio transmissions, named as Radio Frequency (RF) energy harvesting. RF energy scavenging can collect the available RF energy from the surrounding environment and convert it to dc power. Despite the many benefits of this free and ubiquitous energy source for Long-Range Wide-Area Network (LoRaWAN) applications, the energy levels are low and time-varying. This work studies the possibility of utilizing the available RF energy for LoRaWAN applications with the ultimate goal to overcome the problem of the batteries limited lifespan and their negative impact on the environment [2]. The feasibility study is based on measurements carried out in many countries over the last decade [3, 4]. An analytical LoRaWAN energy model is developed based on a Class A LoRa device (Figure 1a) to estimate the power requirements of the application. Due to the low RF energy levels in the environment, the potential of the self-sustainable operation of LoRa devices based on RF energy harvesting strongly depends on the surrounding environment and the performance of the individual components of the sensor node (Figure 1b). It is shown that the sleep current and the capacitor leakage current are significant limiting factors, while LoRa duty cycle and data rate (DR0-DR5) are subject to the available RF energy levels
• On the Impact of Rectifier Topologies on Rectennas performance
  
  • Niotaki Kyriaki
  , 2021, pp.1-4. This work focuses on the impact of the rectifier topology selection on rectennas performance and especially on their RF-dc conversion efficiency. The performance of the main rectifier topologies over a range of input power and output load values is analyzed and the optimum operating conditions for each topology are identified. This work aims to help RF designers to identify and select the most appropriate topology based on their application needs. (10.23919/URSIGASS51995.2021.9560435)
  DOI : 10.23919/URSIGASS51995.2021.9560435
• Challenges and applications of ambient RF Energy Harvesting systems
  
  • Niotaki Kyriaki
  • Georgiadis Apostolos
  , 2021.
• Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes
  
  • Furnon Nicolas
  • Serizel Romain
  • Essid Slim
  • Illina Irina
  , 2021. Speech enhancement promises higher efficiency in ad-hoc microphone arrays than in constrained microphone arrays thanks to the wide spatial coverage of the devices in the acoustic scene. However, speech enhancement in ad-hoc microphone arrays still raises many challenges. In particular, the algorithms should be able to handle a variable number of microphones, as some devices in the array might appear or disappear. In this paper, we propose a solution that can efficiently process the spatial information captured by the different devices of the microphone array, while being robust to a link failure. To do this, we use an attention mechanism in order to put more weight on the relevant signals sent throughout the array and to neglect the redundant or empty channels. (10.23919/EUSIPCO54536.2021.9616358)
  DOI : 10.23919/EUSIPCO54536.2021.9616358
• Smooth nonnegative tensor factorization for multi-sites electrical load monitoring
  
  • Durand Amaury
  • Roueff François
  • Jicquel Jean-Marc
  • Paul Nicolas
  , 2021. The analysis of load curves collected from smart meters is a key step for many energy management tasks ranging from consumption forecasting to customers characterization and load monitoring. In this contribution, we propose a model based on a functional formulation of nonnegative tensor factorization and derive updates for the corresponding optimization problem. We show on the concrete example of multi-sites load curves disaggregation how this formulation is helpful for 1) exhibiting smooth intraday consumption patterns and 2) taking into account external variables such as the outside temperature. The benefits are demonstrated on simulated and real data by exhibiting a meaningful clustering of the observed sites based on the obtained decomposition.
• A Novel Pseudo-Bayesian Approach for Robust Multi-Ridge Detection and Mode Retrieval
  
  • Legros Quentin
  • Fourer Dominique
  , 2021, pp.1925--1929. This paper introduces a novel approach for extracting the elementary components present in an observed nonstationary mixture signal. Our technique based on a pseudo-Bayesian approach operates in the time-frequency plane and sequentially estimates the ridge of each component that is required for mode extraction. We compare our results with those obtained with the state-of-the-art Brevdo method which has shown its efficiency for disentangling multicomponent noisy signals. Our results reveal an improvement of the reconstruction performance when compared to the state of the art.