Graph neural networks (GNNs) are a powerful class of models that learn effective representations over dependencies between entities in a graph. Despite the achievement of GNNs in capturing both long-and short-distance semantics, challenges persist within text classification problems, such as multilingual sentiment analysis. Most existing GNNs methods are unable to capture word ordering and do not effectively support inductive learning with new data. In this work, to handle these challenges, we propose Ind-MSA, an Inductive Multilingual Sentiment Analysis approach. Our initial step involves constructing a single heterogeneous text graph, leveraging diverse information to effectively model the multilingual corpus. Subsequently, the learned word representations are employed to train a Bi-LSTM with attention mechanism, enhancing the proposed approach by incorporating sequential information into the analysis. The proposed approach can capture both short-and long-distance semantics while supporting the word ordering, which is extremely critical in sentiment analysis. Comprehensive experiments on various distinct datasets reveal that Ind-MSA leads to state-of-the-art results, significantly outperforming methods which focus on local consecutive word sequences and global word co-occurrence.

Rebii Jamal, Mounir Ourekouch, Mohammed Erradi. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

We address the problem of checking that computations of a shared memory implementation (with write and read operations) adheres to some given consistency model. It is known that checking conformance to Sequential Consistency (SC) for a given computation is NP-hard, and the same holds for checking Total Store Order (TSO) conformance. This poses a serious issue for the design of scalable verification or testing techniques for these important memory models. In this paper, we tackle this issue by providing an approach that avoids hitting systematically the worst-case complexity. The idea is to consider, as an intermediary step, the problem of checking weaker criteria that are as strong as possible while they are still checkable in polynomial time (in the size of the computation). The criteria we consider are new variations of causal consistency suitably defined for our purpose. The advantage of our approach is that in many cases (1) it can catch violations of SC/TSO early using these weaker criteria that are efficiently checkable, and (2) when a computation is causally consistent (according to our newly defined criteria), the work done for establishing this fact simplifies significantly the work required for checking SC/TSO conformance. We have implemented our algorithms and carried out several experiments on realistic cache-coherence protocols showing the efficiency of our approach.

In big data environments with big number of users and high volume of data, we need to manage the corresponding huge number of security policies. Due to the distributed management of these policies, they may contain several anomalies, such as conflicts and redundancies, which may lead to both safety and availability problems. The distributed systems guided by such security policies produce a huge number of access logs. Due to potential security breaches, the access logs may show the presence of non-allowed accesses. This may also be a consequence of conflicting rules in the security policies. In this paper, we present an ongoing work on developing an environment for verifying and correcting security policies. To make the approach efficient, an access log is used as input to determine suspicious parts of the policy that should be considered. The approach is also made efficient by clustering the policy and the access log and considering separately the obtained clusters. The clustering technique and the use of access log significantly reduces the complexity of the suggested approach, making it scalable for large amounts of data.

Game theory is a powerful tool that has recently been used in networks to improve the end users' quality of experience (e.g. decreased response time, higher delivery rate). In this paper, we propose to use game theory in the context of Content Delivery Networks (CDNs) to organize video contents into clusters having similar request profiles. The popularity of each content in the cluster can be determined from the popularity of the representative of the cluster and used to store the most popular contents close to end users. A group of experts and a decision-maker predict the popularity of the representative of the cluster. This considerably reduces the number of experts used. More precisely, we model the clustering problem as a hedonic coalition formation game where each coalition represents a cluster. The coalition game converges to a stable partition representing a solution of the problem considered. We compare the results of this approach with the clustering obtained by the K-means algorithm. We evaluate the impact of the content profile observation window considered to establish the clustering. We also evaluate the complexity of the proposed algorithm. Simulation results are obtained on traces of a real CDN. Finally, we extend the proposed approach to model an on-line clustering reflecting the CDN dynamics in terms of proposed contents and contents solicitations.

Text spotting, i.e., the localization and recognition of text occurrences in natural images and videos, is a challenging problem in computer vision. Important applications of text spotting are: video indexing, retrieval and search, the support of blind persons in finding their way in unknown environments and reading street and shop signs for autonomously driving vehicles or car license plate recognition in traffic control systems. Recently, the use of deep convolutional neural networks as well as recognizing whole words instead of single characters led to significant progress in the field of text spotting. Furthermore, there is a tendency towards merging and unifying the single steps of the text spotting pipeline. Despite current progress, it is still difficult to recognize in-scene text in comparison to overlaid text. This work gives an overview of the state-of-the-art in text spotting and highlights current breakthroughs and trends.

Wireless Sensor Networks are deployed in different fields of application to gather data on the monitored environment. The Wireless Body Sensor Network (WBSN) is a wireless sensor network designed to monitor a human body vital and environment parameters. The design and development of such WBSN systems for health monitoring have been motivated by costly healthcare and propelled by the development of miniature health monitoring devices. This paper presents the architecture design of a preventive health care monitoring system. This architecture is designed for monitoring multiple patients in a hospital. It is based on a set of mobile data collectors and static sensors for analysis of various patient's parameters. The data collectors need to cooperate together in order to gather the data from the sensor nodes. The point of this paper is how to dynamically and effectively appoint and deploy several data collectors in the hospital to gather the measured data in minimal time. We formulate the problem as a coalitional matching game between patients and data collectors, and we propose a patient-data collector association algorithm that ensures fairness and minimum total course in the stable matchings.

Cloud computing has become a widely used paradigm in many IT domains such as e-health. It offers several advantages to the users, e.g. elasticity, flexibility and the rapid sharing of a huge set of digital data. However, many security and privacy concerns still pose significant challenges. In particular, the most identified problem is how to enforce the user's security policy in the access control of the outsourced data. In fact, cloud environments does not provide facilities to support high level defined security policies. For instance, the swift storage component of openstack supports only fine grained access control to execute a specific action on a specific defined object. In this paper, we designed and implemented a middleware to provide high level security policies while using such swift fine grained primitives. An e-health collaborative application dedicated for remote diagnosis is used to illustrate the suggested approach.

Today collaborative applications may enable collaboration among users from the same or different tenants of a given cloud provider. During such collaborations, the participants need to access and use resources held by other collaborating users. These resources often contain sensitive data. They are meant to be shared only during specific collaborative sessions. A collaborative session is an abstract entity, comprising a set of users, called members of the session, playing the same or different roles. These users may have concurrent access to the shared objects during a session depending on their roles. In this work, we propose an approach that ensures access control to the shared resources in a collaborative session in multi-tenants environments. We suggest CRBAC, the Collaboration Role-based Access Control. CRBAC consists of an extended version of the RBAC model. CRBAC defines new entities to support access control in collaborative sessions. The suggested model has been implemented within Swift component in the open source cloud-computing platform OpenStack.

Wireless Sensor Networks (WSNs) are deployed in many fields of application. Depending on the application requirements, sensor nodes can either be mobile and autonomous or static. In both cases, they are able to cooperate together in order to monitor a given area or some given Points of Interest (PoIs). Static sensor nodes need one or several agent(s) (humans or robots) to deploy them. In this paper, we focus on the deployment of static sensor nodes in an area containing obstacles, using two mobile robots. We want to minimize the time needed by the two robots to deploy all the sensor nodes and to return to their starting position. We require that each sensor node is placed at a PoI position, no PoI position is empty and no PoI position is occupied by more than one sensor node. The problem consists in determining the best strategy for each robot in order to meet these constraints. We adopt a game theory approach to solve this problem.

To ensure connectivity in highly sparse Wireless Sensor Networks (WSNs), we consider a Ferry-assisted Wireless Sensor Network (FWSN). In our FWSN, message ferries moving along concentric annulus collect the static sensors generated packets and propagate them throughout a ferry-to-ferry forwarding schema to the sink. In this paper we present a queueing model to study and analyze the FWSN behavior. We will adapt a queuing model with finite queues which will allow us to analyze the network behavior in tens of packet loss using an analytic model. The objective of this work is to provide a way to optimize the energy consumption for each individual sensor. In our approach we consider a sensor Ferry, which is a mobile sensor with the capacity to provide the control operation upon the other fixed sensors within to network. Therefor, these fixed sensors will have to perform less control operations which will reduce their individual energy consumption. By doing so, this will automatically impact positively on to the lifetime of the network.

Information systems must be controlled by security policies to protect them from undue accesses. Security policies are often designed by rules expressed using informal text, which implies ambiguities and inconsistencies in security rules. Our objective in this paper is to develop a formal approach to design and analyze security policies. We propose a procedure that synthesizes an automaton which implements a given security policy. Our automata-based approach can be a common basis to analyze several aspects of security policies. We use our automata-based approach to develop three analysis procedures to: verify completeness of a security policy, detect anomalies in a security policy, and detect functional discrepancies between several implementations of a security policy. We illustrate our approach using examples of security policies for a firewall.

In this paper, we present PDP, a distributed polling protocol that enables a set of participants to gather their opinion on a common interest without revealing their point of view. PDP does not rely on any centralized authority or on heavyweight cryptography. PDP is an overlay-based protocol where a subset of participants may use a simple sharing scheme to express their votes. In a system of M participants arranged in groups of size N where at least 2k-1 participants are honest, PDP bounds the probability for a given participant to have its vote recovered with certainty by a coalition of B dishonest participants by π(B/N)(k+1), where π is the proportion of participants splitting their votes, and k a privacy parameter. PDP bounds the impact of dishonest participants on the global outcome by 2(kα + BN), where represents the number of dishonest nodes using the sharing scheme.

The demand for the ubiquitous service is increasing due to the rapidly growing demand for increased data rates, mobile Internet and the diversity of wireless communication technologies. Also due to the challenges to interconnect heterogeneous network technologies and to offer ubiquitous services, telecommunications operators look after the best way to provide continuity of service during handover and how to give the mobile client the possibility to get the best connection anywhere and anytime. In this paper we propose an architecture and its implementation which guarantees the continuity of service during a communication in the context of heterogeneous access network technologies. The suggested solution named HaVe-2W3G (Handover Vertical WLAN WiMAX 3G) ensures a Vertical handover between heterogeneous access networks technologies: WLAN, WiMAX and 3G. A performance evaluation of such implementation is shown using a streaming application.*

Recently, object-oriented specifications of distributed systems has gained more attention. The object-oriented approach is known for its flexibility for system construction. However, one of the major challenges is to provide facilities for the dynamic modifications of such specifications during the development and maintenance process. Yet, current work has not addressed the dynamic modifications of specifications of distributed systems. In this paper, we are concerned with formal description techniques that allow for the development and dynamic modification of executable specifications. A two-level model for the evolution of large object-oriented specifications is introduced. The first deals with the dynamic modifications of types (classes), while the second deals with modifications of modules. We have defined a set of structural and behavioral constraints to ensure specification consistency after modification at both levels. To allow dynamic modification of types and modules, we have developed a reflective object-oriented specification language which uses meta-objects to support the modification operations. In this language, types and modules are objects.

The object-oriented approach is known by its flexibility for system construction. Current work has not addressed the dynamic modifications of specifications of distributed systems. We are concerned with formal description techniques that allow for the development and the dynamic modification of executable specifications. A two level model for the evolution of large object-oriented specifications is introduced. The first level deals with the dynamic modifications of types (classes), while the second level deals with modifications of modules. We have defined a set of structural and behavioral constraints to ensure the specification consistency after its modification at both levels. To allow for dynamic modification of types and modules, we have developed a reflective object-oriented specification language (Mondel) which uses meta objects to support the modification operations.>

It is noted that the evolution of specifications is necessary to accommodate the evolution of requirements and design decisions during the software development and maintenance process. The authors are concerned with formal description techniques that allow the development of executable specifications, especially executable object-oriented specifications of distributed systems. They propose a two-level model for the evolution of large object-oriented specifications. The first level deals with the dynamic modification of types (classes) while the second level deals with the modification of modules. To allow for dynamic modification of types and modules, the authors have developed a reflection-based technique using meta-objects in which the modification operations are defined. In their approach, they have defined a set of structural and behaviour constraints to ensure the specification consistency after its modification at both levels.>

Improvements both in technology and in user-oriented software have shown the feasibility of new kinds of non-procedural languages. However, interaction between end-user and data should rely more and more on graphical languages and, particularly, on 'iconic” languages. In the following we review and analyze the forces which are at the origin of changes in the user environment. We give the main specifications of an iconic interface and a command language based on icons. Examples are given in a medical environment.