Bechara AL Bouna

Université Antonine | UA · Computer Science

Image obfuscation techniques (e.g., pixelation, blurring and masking,...) have been developed to protect sensitive information in images (e.g. individuals’ faces). In a previous work, we designed a recommendation framework that evaluates the robustness of image obfuscation techniques and recommends the most resilient obfuscation against Deep-Learni...

This paper investigates the problem of forecasting multivariate aggregated human mobility while preserving the privacy of the individuals concerned. Differential privacy, a state-of-the-art formal notion, has been used as the privacy guarantee in two different and independent steps when training deep learning models. On one hand, we considered grad...

This paper investigates the problem of collecting multidimensional data throughout time (i.e., longitudinal studies) for the fundamental task of frequency estimation under Local Differential Privacy (LDP) guarantees. Contrary to frequency estimation of a single attribute, the multidimensional aspect demands particular attention to the privacy budge...

This paper investigates the problem of forecasting multivariate aggregated human mobility while preserving the privacy of the individuals concerned. Differential privacy, a state-of-the-art formal notion, has been used as the privacy guarantee in two different and independent steps when training deep learning models. On one hand, we considered \tex...

A particularly challenging problem for data anonymization is dealing with transactional data. Most anonymization methods assume homogeneous, independent and identically distributed (i.i.d.) data; “flattening” transactional data to satisfy this model results in wide, sparse data that does not anonymize well with traditional techniques. While there h...

This paper investigates the problem of collecting multidimensional data throughout time (i.e., longitudinal studies) for the fundamental task of frequency estimation under local differential privacy (LDP). Contrary to frequency estimation of a single attribute (the majority of the works), the multidimensional aspect imposes to pay particular attent...

With local differential privacy (LDP), users can privatize their data and thus guarantee privacy properties before transmitting it to the server (a.k.a. the aggregator). One primary objective of LDP is frequency (or histogram) estimation, in which the aggregator estimates the number of users for each possible value. In practice, when a study with r...

With local differential privacy (LDP), users can privatize their data and thus guarantee privacy properties before transmitting it to the server (a.k.a. the aggregator). One primary objective of LDP is frequency (or histogram) estimation, in which the aggregator estimates the number of users for each possible value. In practice, when a study with r...

Longitudinal studies of human mobility could allow an understanding of human behavior on a vast scale. Mobile phone data call detail records (CDRs) have emerged as a prospective data source for such an important task. Nevertheless, there are significant risks when it comes to collecting this type of data, as human mobility has proven to be quite un...

In this article, we present a privacy-preserving technique for user-centric multi-release graphs. Our technique consists of sequentially releasing anonymized versions of these graphs under Blowfish Privacy. To do so, we introduce a graph model that is augmented with a time dimension and sampled at discrete time steps. We show that the direct applic...

Nowadays, social media runs a significant portion of people’s daily lives. Millions of people use social media applications to share photos. The massive volume of images shared on social media presents serious challenges and requires large computational infrastructure to ensure successful data processing. However, an image gets distorted somehow du...

Les travaux présentés ici visent à prédire le nombre d'interventions des pompiers par Communauté d'Agglomération tout en respectant la vie privée des utilisateurs. Une approche basée sur la confidentialité différentielle locale a été développée pour anonymiser les données de localisation, puis une approche d'apprentissage supervisé a été mise en pl...

Les travaux présentés ici visent à prédire le nombre d'interventions des pompiers par Communauté d'Agglomération tout en respectant la vie privée des utilisateurs. Une approche basée sur la confidentialité différentielle locale a été développée pour anonymiser les données de localisation, puis une approche d'apprentissage supervisé a été mise en pl...

Modeling and understanding people's mobility at a temporal and geographical space are very strict requirements for developing better strategies of urban public and private transportation systems as well as establishing improved business techniques. This work proposes a random-search based approach to instantiate statistical indicators through an im...

Modeling and understanding people's mobility at a temporal and geographical space are very strict requirements for developing better strategies of urban public and private transportation systems as well as establishing improved business techniques. This work proposes a random-search based approach to instantiate statistical indicators through an im...

Modeling and understanding people's mobility at a temporal and geographical space are very strict requirements for developing better strategies of urban public and private transportation systems as well as establishing improved business techniques. This work proposes a random-search based approach to instantiate statistical indicators through an im...

Statistical studies on the number and types of firefighter interventions by region are essential to improve service to the population. It is also a preliminary step if we want to predict these interventions in order to optimize the placement of human and material resources of fire departments, for example. However, this type of data is sensitive an...

Data publishing is a challenging task for privacy preservation constraints. To ensure privacy, many anonymization techniques have been proposed. They differ in terms of the mathematical properties they verify and in terms of the functional objectives expected. Disassociation is one of the techniques that aim at anonymizing of set-valued datasets (e...

Disassociation is a bucketization based anonymization technique that divides a set-valued dataset into several clusters to hide the link between individuals and their complete set of items. It increases the utility of the anonymized dataset, but on the other side, it raises many privacy concerns, one in particular, is when the items are tightly cou...

Computer vision applications such as object detection and recognition, allow machines to visualize and perceive their environments. Nevertheless, these applications are guided by learning-based methods that require capturing, storing and processing large amounts of images thus rendering privacy and anonymity a major concern. In return, image obfusc...

Data publishing is a challenging task from the privacy point of view. Different anonymization techniques are proposed in the literature to preserve privacy in accordance with some mathematical constraints. Disassociation is one of the anonymization techniques that relies on the km - anonymity privacy constraint to guarantee a certain level of priva...

Disassociation introduced by Terrovitis et al. is a bucketization based anonimyzation technique that divides a set-valued dataset into several clusters to hide the link between individuals and their complete set of items. It increases the utility of the anonymized dataset, but on the other side, it raises many privacy concerns, one in particular, i...

In this paper, our aim is to design and develop an anonymous full-duplex image classification framework under Differential Privacy. We work under the assumption that both, the cloud and the querier are semi-trusted entities, thus their data should remain safe and confidential. That is, neither the querier nor the cloud should be able to link a part...

In this paper, we address the correlation problem in the anonymization of transactional data streams. We propose a bucketization-based technique, entitled (k,l)-clustering to prevent such privacy breaches by ensuring that the same k individuals remain grouped together over the entire anonymized stream. We evaluate our algorithm in terms of utility...

Data anonymization is gaining much attention these days as it provides the fundamental requirements to safely outsource datasets containing identifying information. While some techniques add noise to protect privacy others use generalization to hide the link between sensitive and non-sensitive information or separate the dataset into clusters to ga...

In cryptography, the Cipher Block Chaining (CBC), one of the most commonly used mode in recent years, is a mode of operation that uses a block cipher to provide confidentiality or authenticity. In our previous research work, we have shown that this mode of operation exhibits, under some conditions, a chaotic behaviour. We have studied this behaviou...

The performance of some state-of-the-art steganalysers is investigated according to various parameters, encompassing the choice of the steganographier, its payload, and the type of images both during training and testing stage. All these parameters are changed to determine their effects on steganalysis performance. Experiments are performed using l...

In this paper, we study the privacy breach caused by unsafe correlations in transactional data where individuals have multiple tuples in a dataset. We provide two safety constraints to guarantee safe correlation of the data: (1) the safe grouping constraint to ensure that quasi-identifier and sensitive partitions are bounded by l-diversity and (2)...

A fundamental aspect of all social networks is information sharing. It is one of the most common forms of online interaction that is tightly associated with social media preservation and information disclosure. As such, information sharing is commonly viewed as a key enabler for social media preservation tasks. In the current situation, where infor...

Multimedia documents sharing and outsourcing have become part of the routine activity of many individuals and companies. Such data sharing puts at risk the privacy of individuals, whose identities need to be kept secret, when adversaries get the ability to associate the multimedia document’s content to possible trail of information left behind by t...

In this paper, we present a study to counter privacy violation due to unsafe data correlation. We propose a safe correlation requirement to keep correlated values bounded by l-diversity and evaluate the trade-off to be made for the sake of a strong privacy guarantee. Finally, we present a correlation sanitization algorithm that enforces our safety...

Recently, multimedia and internet technologies have been in rapid development. Multimedia objects, such as images, video, audio tracks and multimedia documents, have been widely used and are in remarkable growth. Almost everyone on social network publishes or has some multimedia objects stored somewhere. Although multimedia objects are of different...

Outsourcing social multimedia documents is a growing practice among several companies in a way to shift their business globally. It is a cost-effective process where those companies tend to gain more profits disregarding eventual privacy risks. In fact, several case studies have showed that adversaries are capable of identify-ing individuals, whose...

Nowadays, social network are tremendously spreading their tentacles over the web community providing appropriate and well adapted tools for sharing images. A fundamental glitch to consider is their ability to provide suitable techniques to preserve individuals' privacy. Indeed, there is an urgent need to guarantee privacy by making available to end...

In this paper, we address privacy breaches in transactional data where individuals have multiple tuples in a dataset. We provide a safe grouping principle to ensure that correlated values are grouped together in unique partitions that enforce l-diversity at the level of individuals. We conduct a set of experiments to evaluate privacy breach and the...

In this paper, we identify a new and challenging application for the growing field of research on data anonymization and secure outsourcing of storage and computations to the cloud. Network flow data analysis is of high importance for network monitoring and management. Network monitoring applications reveal new challenges not yet addressed in the s...

This volume aims at assessing the current approaches and technologies, as well as to outline the major challenges and future perspectives related to the security and privacy protection of social networks. It provides the reader with an overview of the state-of-the art techniques, studies, and approaches as well as outlining future directions in thi...

Sharing and publishing images and photos have become the trend of nowadays (social networks, messengers, etc.). Providing appropriate techniques to preserve privacy and protect content of sensitive and private images is an essential need. In this paper, we present a novel security model for image content protection. In our model, we provide dynamic...

In this paper, we propose a novel technique for privacy preserving in multimedia databases. Our technique is based on a multimedia co-occurrence matrix and a tree augmented naive Bayesian classifier (TAN) to detect possible data associations making confidential multimedia objects at risk.

The tremendous sharing of multimedia objects on the web shed the light on several privacy concerns related in essence to the safe publishing of end users' personal data. Providing techniques to protect multimedia objects faces several difficulties due to multimedia objects' heterogeneous and complex structure on one hand, and on the other hand, the...

Indirect access to protected information has been one of the key challenges facing the international community for the last decade. Providing techniques to control direct access to sensitive information remain insufficient against inference channels established when legitimate data reveal classified facts hidden from unauthorized users. Several tec...

Context-aware and Ambient Intelligence environments represent one of the emerging issues in the last decade. In such intelligent environments, information is gathered to provide, on one hand, autonomic and easy to manage applications, and, on the other, secured access controlled environments. Several approaches have been defined in the literature t...

Recently ubiquitous technology has invaded almost every aspect of the modern life. Several application domains, have integrated ubiquitous technology to make the management of resources a dynamic task. However, the need for adequate and enforced authentication and access control models to provide safe access to sensitive information remains a criti...

In this paper, we describe our Multimedia Context based Security Engine (MCSE) which is a Java Based Prototype able to integrate multimedia context in order to enforce access control policies. The prototype provides supervised access to a database containing sensitive viral images.

Access control models are becoming increasingly important in several application domains especially in distributed environments like those addressed by Web Services. Established approaches such as DAC [16] , MAC [16] RBAC [11, 12, 22] and others [6, 5, 15, 1] suggest representing users in different ways (labels, roles, credentials, etc.) in order t...

The rapid development of information systems has lead in many ways to the definition of advanced authorization and access control models. Recent models have considered context (such as time, location, age, etc.) as key issue to allow flexible and dynamic policy specification. However, these models are application-dependent, text-based, complex to m...

Cyber terrorism is one of the emergent issues to handle in the domain of security and access control models. Cyber Terrorist attacks on information systems are growing further and becoming significantly effective. Multimedia object retrieval systems are considered one of many targets tolerable for such attacks due to the fact that they are being in...

Cyber terrorism is one of the emergent issues to handle in the domain of security and access control models. Cyber Terrorist attacks on information systems are growing further and becoming significantly effective. Multimedia object retrieval systems are considered one of many targets tolerable for such attacks due to the fact that they are being in...

Exchanging multimedia objects between wide ranges of distributed applications, web services, and end-users is rapidly increasing in several application domains (medicine, surveillance, e-learning, etc.). In confidential applications, one of the emergent problems to deal with is data authorization and access control. Several textual-oriented authori...