arXiv subjects

Fabrice Labeau

Publications and source records attributed to Fabrice Labeau.

At least 19 recordsLinked to original sources

arXiv2023

Preserving Privacy in GANs Against Membership Inference Attack

Generative Adversarial Networks (GANs) have been widely used for generating synthetic data for cases where there is a limited size real-world dataset or when data holders are unwilling to share their data samples. Recent works showed that GANs, due to overfitting and memorization, might leak information regarding their training data samples. This makes GANs vulnerable to Membership Inference Attacks (MIAs). Several defense strategies have been proposed in the literature to mitigate this privacy issue. Unfortunately, defense strategies based on differential privacy are proven to reduce extensively the quality of the synthetic data points. On the other hand, more recent frameworks such as PrivGAN and PAR-GAN are not suitable for small-size training datasets. In the present work, the overfitting in GANs is studied in terms of the discriminator, and a more general measure of overfitting based on the Bhattacharyya coefficient is defined. Then, inspired by Fano's inequality, our first defense mechanism against MIAs is proposed. This framework, which requires only a simple modification in the loss function of GANs, is referred to as the maximum entropy GAN or MEGAN and significantly improves the robustness of GANs to MIAs. As a second defense strategy, a more heuristic model based on minimizing the information leaked from generated samples about the training data points is presented. This approach is referred to as mutual information minimization GAN (MIMGAN) and uses a variational representation of the mutual information to minimize the information that a synthetic sample might leak about the whole training data set. Applying the proposed frameworks to some commonly used data sets against state-of-the-art MIAs reveals that the proposed methods can reduce the accuracy of the adversaries to the level of random guessing accuracy with a small reduction in the quality of the synthetic data samples.

cs.LG↗

arXiv2023

$α$-Mutual Information: A Tunable Privacy Measure for Privacy Protection in Data Sharing

This paper adopts Arimoto's $α$-Mutual Information as a tunable privacy measure, in a privacy-preserving data release setting that aims to prevent disclosing private data to adversaries. By fine-tuning the privacy metric, we demonstrate that our approach yields superior models that effectively thwart attackers across various performance dimensions. We formulate a general distortion-based mechanism that manipulates the original data to offer privacy protection. The distortion metrics are determined according to the data structure of a specific experiment. We confront the problem expressed in the formulation by employing a general adversarial deep learning framework that consists of a releaser and an adversary, trained with opposite goals. This study conducts empirical experiments on images and time-series data to verify the functionality of $α$-Mutual Information. We evaluate the privacy-utility trade-off of customized models and compare them to mutual information as the baseline measure. Finally, we analyze the consequence of an attacker's access to side information about private data and witness that adapting the privacy measure results in a more refined model than the state-of-the-art in terms of resiliency against side information.

cs.LG↗

arXiv2022

Cardiotocography Signal Abnormality Detection based on Deep Unsupervised Models

Cardiotocography (CTG) is a key element when it comes to monitoring fetal well-being. Obstetricians use it to observe the fetal heart rate (FHR) and the uterine contraction (UC). The goal is to determine how the fetus reacts to the contraction and whether it is receiving adequate oxygen. If a problem occurs, the physician can then respond with an intervention. Unfortunately, the interpretation of CTGs is highly subjective and there is a low inter- and intra-observer agreement rate among practitioners. This can lead to unnecessary medical intervention that represents a risk for both the mother and the fetus. Recently, computer-assisted diagnosis techniques, especially based on artificial intelligence models (mostly supervised), have been proposed in the literature. But, many of these models lack generalization to unseen/test data samples due to overfitting. Moreover, the unsupervised models were applied to a very small portion of the CTG samples where the normal and abnormal classes are highly separable. In this work, deep unsupervised learning approaches, trained in a semi-supervised manner, are proposed for anomaly detection in CTG signals. The GANomaly framework, modified to capture the underlying distribution of data samples, is used as our main model and is applied to the CTU-UHB dataset. Unlike the recent studies, all the CTG data samples, without any specific preferences, are used in our work. The experimental results show that our modified GANomaly model outperforms state-of-the-arts. This study admit the superiority of the deep unsupervised models over the supervised ones in CTG abnormality detection.

eess.SP↗

arXiv2022

Adversarial Robustness via Fisher-Rao Regularization

Adversarial robustness has become a topic of growing interest in machine learning since it was observed that neural networks tend to be brittle. We propose an information-geometric formulation of adversarial defense and introduce FIRE, a new Fisher-Rao regularization for the categorical cross-entropy loss, which is based on the geodesic distance between the softmax outputs corresponding to natural and perturbed input features. Based on the information-geometric properties of the class of softmax distributions, we derive an explicit characterization of the Fisher-Rao Distance (FRD) for the binary and multiclass cases, and draw some interesting properties as well as connections with standard regularization metrics. Furthermore, for a simple linear and Gaussian model, we show that all Pareto-optimal points in the accuracy-robustness region can be reached by FIRE while other state-of-the-art methods fail. Empirically, we evaluate the performance of various classifiers trained with the proposed loss on standard datasets, showing up to a simultaneous 1\% of improvement in terms of clean and robust performances while reducing the training time by 20\% over the best-performing methods.

cs.LG↗

arXiv2021

Real-Time Privacy-Preserving Data Release for Smart Meters

Smart Meters (SMs) are able to share the power consumption of users with utility providers almost in real-time. These fine-grained signals carry sensitive information about users, which has raised serious concerns from the privacy viewpoint. In this paper, we focus on real-time privacy threats, i.e., potential attackers that try to infer sensitive information from SMs data in an online fashion. We adopt an information-theoretic privacy measure and show that it effectively limits the performance of any attacker. Then, we propose a general formulation to design a privatization mechanism that can provide a target level of privacy by adding a minimal amount of distortion to the SMs measurements. On the other hand, to cope with different applications, a flexible distortion measure is considered. This formulation leads to a general loss function, which is optimized using a deep learning adversarial framework, where two neural networks -- referred to as the releaser and the adversary -- are trained with opposite goals. An exhaustive empirical study is then performed to validate the performance of the proposed approach and compare it with state-of-the-art methods for the occupancy detection privacy problem. Finally, we also investigate the impact of data mismatch between the releaser and the attacker.

eess.SP↗

arXiv2021

Privacy-Cost Management in Smart Meters Using Deep Reinforcement Learning

Smart meters (SMs) play a pivotal rule in the smart grid by being able to report the electricity usage of consumers to the utility provider (UP) almost in real-time. However, this could leak sensitive information about the consumers to the UP or a third-party. Recent works have leveraged the availability of energy storage devices, e.g., a rechargeable battery (RB), in order to provide privacy to the consumers with minimal additional energy cost. In this paper, a privacy-cost management unit (PCMU) is proposed based on a model-free deep reinforcement learning algorithm, called deep double Q-learning (DDQL). Empirical results evaluated on actual SMs data are presented to compare DDQL with the state-of-the-art, i.e., classical Q-learning (CQL). Additionally, the performance of the method is investigated for two concrete cases where attackers aim to infer the actual demand load and the occupancy status of dwellings. Finally, an abstract information-theoretic characterization is provided.

eess.SP↗

arXiv2021

Deep Directed Information-Based Learning for Privacy-Preserving Smart Meter Data Release

The explosion of data collection has raised serious privacy concerns in users due to the possibility that sharing data may also reveal sensitive information. The main goal of a privacy-preserving mechanism is to prevent a malicious third party from inferring sensitive information while keeping the shared data useful. In this paper, we study this problem in the context of time series data and smart meters (SMs) power consumption measurements in particular. Although Mutual Information (MI) between private and released variables has been used as a common information-theoretic privacy measure, it fails to capture the causal time dependencies present in the power consumption time series data. To overcome this limitation, we introduce the Directed Information (DI) as a more meaningful measure of privacy in the considered setting and propose a novel loss function. The optimization is then performed using an adversarial framework where two Recurrent Neural Networks (RNNs), referred to as the releaser and the adversary, are trained with opposite goals. Our empirical studies on real-world data sets from SMs measurements in the worst-case scenario where an attacker has access to all the training data set used by the releaser, validate the proposed method and show the existing trade-offs between privacy and utility.

cs.LG↗

arXiv2021

On the Impact of Side Information on Smart Meter Privacy-Preserving Methods

Smart meters (SMs) can pose privacy threats for consumers, an issue that has received significant attention in recent years. This paper studies the impact of Side Information (SI) on the performance of distortion-based real-time privacy-preserving algorithms for SMs. In particular, we consider a deep adversarial learning framework, in which the desired releaser (a recurrent neural network) is trained by fighting against an adversary network until convergence. To define the loss functions, two different approaches are considered: the Causal Adversarial Learning (CAL) and the Directed Information (DI)-based learning. The main difference between these approaches is in how the privacy term is measured during the training process. On the one hand, the releaser in the CAL method, by getting supervision from the actual values of the private variables and feedback from the adversary performance, tries to minimize the adversary log-likelihood. On the other hand, the releaser in the DI approach completely relies on the feedback received from the adversary and is optimized to maximize its uncertainty. The performance of these two algorithms is evaluated empirically using real-world SMs data, considering an attacker with access to SI (e.g., the day of the week) that tries to infer the occupancy status from the released SMs data. The results show that, although they perform similarly when the attacker does not exploit the SI, in general, the CAL method is less sensitive to the inclusion of SI. However, in both cases, privacy levels are significantly affected, particularly when multiple sources of SI are included.

eess.SP↗

arXiv2021

Privacy-Cost Management in Smart Meters with Mutual Information-Based Reinforcement Learning

The rapid development and expansion of the Internet of Things (IoT) paradigm has drastically increased the collection and exchange of data between sensors and systems, a phenomenon that raises serious privacy concerns in some domains. In particular, Smart Meters (SMs) share fine-grained electricity consumption of households with utility providers that can potentially violate users' privacy as sensitive information is leaked through the data. In order to enhance privacy, the electricity consumers can exploit the availability of physical resources such as a rechargeable battery (RB) to shape their power demand as dictated by a Privacy-Cost Management Unit (PCMU). In this paper, we present a novel method to learn the PCMU policy using Deep Reinforcement Learning (DRL). We adopt the mutual information (MI) between the user's demand load and the masked load seen by the power grid as a reliable and general privacy measure. Unlike previous studies, we model the whole temporal correlation in the data to learn the MI in its general form and use a neural network to estimate the MI-based reward signal to guide the PCMU learning process. This approach is combined with a model-free DRL algorithm known as the Deep Double Q-Learning (DDQL) method. The performance of the complete DDQL-MI algorithm is assessed empirically using an actual SMs dataset and compared with simpler privacy measures. Our results show significant improvements over state-of-the-art privacy-aware demand shaping methods.

eess.SP↗

arXiv2021

Learning Sparse Privacy-Preserving Representations for Smart Meters Data

Fine-grained Smart Meters (SMs) data recording and communication has enabled several features of Smart Grids (SGs) such as power quality monitoring, load forecasting, fault detection, and so on. In addition, it has benefited the users by giving them more control over their electricity consumption. However, it is well-known that it also discloses sensitive information about the users, i.e., an attacker can infer users' private information by analyzing the SMs data. In this study, we propose a privacy-preserving approach based on non-uniform down-sampling of SMs data. We formulate this as the problem of learning a sparse representation of SMs data with minimum information leakage and maximum utility. The architecture is composed of a releaser, which is a recurrent neural network (RNN), that is trained to generate the sparse representation by masking the SMs data, and an utility and adversary networks (also RNNs), which help the releaser to minimize the leakage of information about the private attribute, while keeping the reconstruction error of the SMs data minimum (i.e., maximum utility). The performance of the proposed technique is assessed based on actual SMs data and compared with uniform down-sampling, random (non-uniform) down-sampling, as well as the state-of-the-art in privacy-preserving methods using a data manipulation approach. It is shown that our method performs better in terms of the privacy-utility trade-off while releasing much less data, thus also being more efficient.

eess.SP↗

arXiv2020

Privacy-Preserving Adversarial Network (PPAN) for Continuous non-Gaussian Attributes

A privacy-preserving adversarial network (PPAN) was recently proposed as an information-theoretical framework to address the issue of privacy in data sharing. The main idea of this model was using mutual information as the privacy measure and adversarial training of two deep neural networks, one as the mechanism and another as the adversary. The performance of the PPAN model for the discrete synthetic data, MNIST handwritten digits, and continuous Gaussian data was evaluated compared to the analytically optimal trade-off. In this study, we evaluate the PPAN model for continuous non-Gaussian data where lower and upper bounds of the privacy-preserving problem are used. These bounds include the Kraskov (KSG) estimation of entropy and mutual information that is based on k-th nearest neighbor. In addition to the synthetic data sets, a practical case for hiding the actual electricity consumption from smart meter readings is examined. The results show that for continuous non-Gaussian data, the PPAN model performs within the determined optimal ranges and close to the lower bound.

eess.SP↗

arXiv2019

Performance Analysis of DF Cooperative Relaying over Bursty Impulsive Noise Channel

In this article, we consider the performance analysis of a decode-and-forward (DF) cooperative relaying (CR) scheme over channels impaired by bursty impulsive noise. Although, Middleton class-A model and Bernoulli-Gaussian model give good results to generate a sample distribution of impulsive noise, they fail in replicating the bursty behavior of impulsive noise, as encountered for instance within power substations. To deal with that, we adopt a two-state Markov-Gaussian process for the noise distribution. For this channel, we evaluate the bit error rate (BER) performance of direct transmission (DT) and a DF relaying scheme using M-ary phase shift keying (M-PSK) modulation in the presence of Rayleigh fading with a maximum a posteriori (MAP) receiver. From the obtained results, it is seen that the DF CR scheme in bursty impulsive noise channel still achieves the space diversity and performs significantly better than DT under the same power consumption. Moreover, the proposed MAP receiver attains the lower bound derived for DF CR scheme, and leads to large performance gains compared to the conventional receiving criteria which were optimized for additive white Gaussian noise (AWGN) channel and memoryless impulsive noise channel.

eess.SP↗

arXiv2018

Rate Adaptation for Secure HARQ Protocols

This paper investigates the incremental-redundancy hybrid-automatic repeat request (IR-HARQ) transmission over independent block-fading channels in the presence of an eavesdropper, where the secrecy of the transmission is ensured via introduction of dummy-messages. Since the encoder only knows the statistics of the channel state, the secrecy and the reliability are defined in a probabilistic framework. Unlike previous works on this subject, we design a coding strategy tailored to IR-HARQ by splitting the dummy-message rate over several rate parameters. These additional degrees of freedom improve the match between the dummy-message rates and the realizations of the eavesdropper channels. We evaluate the performance in terms of secrecy outage probability, connection outage probability and throughput and we compare it with the benchmark paper by Tang et al. Numerical examples illustrate that, comparing to existing alternatives, splitting of the dummy-message rate provides higher throughput and lower expected duration/average delay.

cs.IT↗

arXiv2017

Opportunistic Relaying without CSI: Optimizing Variable-Rate HARQ

We analyze the opportunistic relaying based on HARQ transmission over the block-fading channel with absence of channel state information (CSI) at the transmitter nodes. We assume that both the source and the relay are allowed to vary their transmission rate between the HARQ transmission rounds. We solve the problem of throughput maximization with respect to the transmission rates using double-recursive Dynamic Programming. Simplifications are also proposed to diminish the complexity of the optimization. The numerical results confirm that the variable-rate HARQ can increase the throughput significantly comparing to its fixed-rate counterpart.

cs.IT↗

arXiv2015

Micro Service Cloud Computing Pattern for Next Generation Networks

The falling trend in the revenue of traditional telephony services has attracted attention to new IP based services. The IP Multimedia System (IMS) is a key architecture which provides the necessary platform for delivery of new multimedia services. However, current implementations of IMS do not offer automatic scalability or elastisity for the growing number of customers. Although the cloud computing paradigm has shown many promising characteristics for web applications, it is still failing to meet the requirements for telecommunication applications. In this paper, we present some related cloud computing patterns and discuss their adaptations for implementation of IMS or other telecommunication systems.

cs.DC↗

arXiv2015

Analytic MMSE Bounds in Linear Dynamic Systems with Gaussian Mixture Noise Statistics

Using state-space representation, mobile object positioning problems can be described as dynamic systems, with the state representing the unknown location and the observations being the information gathered from the location sensors. For linear dynamic systems with Gaussian noise, the Kalman filter provides the Minimum Mean-Square Error (MMSE) state estimation by tracking the posterior. Hence, by approximating non-Gaussian noise distributions with Gaussian Mixtures (GM), a bank of Kalman filters or Gaussian Sum Filter (GSF), can provide the MMSE state estimation. However, the MMSE itself is not analytically tractable. Moreover, the general analytic bounds proposed in the literature are not tractable for GM noise statistics. Hence, in this work, we evaluate the MMSE of linear dynamic systems with GM noise statistics and propose its analytic lower and upper bounds. We provide two analytic upper bounds which are the Mean-Square Errors (MSE) of implementable filters, and we show that based on the shape of the GM noise distributions, the tighter upper bound can be selected. We also show that for highly multimodal GM noise distributions, the bounds and the MMSE converge. Simulation results support the validity of the proposed bounds and their behavior in limits.

eess.SY↗

arXiv2014

A New Reduction Scheme for Gaussian Sum Filters

In many signal processing applications it is required to estimate the unobservable state of a dynamic system from its noisy measurements. For linear dynamic systems with Gaussian Mixture (GM) noise distributions, Gaussian Sum Filters (GSF) provide the MMSE state estimate by tracking the GM posterior. However, since the number of the clusters of the GM posterior grows exponentially over time, suitable reduction schemes need to be used to maintain the size of the bank in GSF. In this work we propose a low computational complexity reduction scheme which uses an initial state estimation to find the active noise clusters and removes all the others. Since the performance of our proposed method relies on the accuracy of the initial state estimation, we also propose five methods for finding this estimation. We provide simulation results showing that with suitable choice of the initial state estimation (based on the shape of the noise models), our proposed reduction scheme provides better state estimations both in terms of accuracy and precision when compared with other reduction methods.

eess.SY↗

arXiv2014

Medically Relevant Criteria used in EEG Compression for Improved Post-Compression Seizure Detection

Biomedical signals aid in the diagnosis of different disorders and abnormalities. When targeting lossy compression of such signals, the medically relevant information that lies within the data should maintain its accuracy and thus its reliability. In fact, signal models that are inspired by the bio-physical properties of the signals at hand allow for a compression that preserves more naturally the clinically significant features of these signals. In this paper, we illustrate this through the example of EEG signals; more specifically, we analyze three specific lossy EEG compression schemes. These schemes are based on signal models that have different degrees of reliance on signal production and physiological characteristics of EEG. The resilience of these schemes is illustrated through the performance of seizure detection post compression.

cs.IT↗