As our reliance on digital technologies continues to grow, so does the urgency of bolstering our cyber-defenses against the rising threats posed by malicious entities. Existing cybersecurity frameworks and databases such as MITRE ATT&CK and Common Vulnerabilities and Exposures (CVE) offer valuable insights that can assist in mitigating these threats effectively. However, the aforementioned CVE and MITRE ATT &CK solutions operate in silos. We argue that automatically linking the vulnerabilities listed in CVE database to MITRE ATT &CK adversarial techniques and tactics, and in particular the updated ones, will offer crucial and valuable information for blue teams seeking to enhance their cybersecurity defense against cyberattacks. The main objective of this paper is to offer a proactive insight into an attacker's next move by studying ex-isting ML/DL approaches developed to predicting the association between MITRE techniques and CVE in terms of reproducibility, performance analysis, and possible improvements. For the latter aspect, data augmentation and hyperparameter tuning techniques have been used and the obtained results showed significant improvements.

As our dependence on digital technologies continues to expand, the need to strengthen our cyber defenses against the increasing threats posed by malicious entities becomes more critical. While existing cybersecurity frameworks and databases like MITRE ATT&CK and Common Vulnerabilities and Exposures (CVE) offer valuable insights for effective threat mitigation, they often operate independently, leading to siloed information. We assert that the automatic linking of vulnerabilities from the CVE database to MITRE ATT&CK adversarial techniques and tactics, particularly focusing on new ones, can provide essential information to empower blue teams in enhancing their cybersecurity defenses against cyberattacks. Gaining proactive insight into an attacker’s potential next moves is pivotal for effective defense strategies. Therefore, we introduce in this paper GuardLink, a dynamic approach for linking CVE identifiers (IDs) to MITRE ATT&CK techniques. We first studied, reproduced, evaluated, and improved state of the art models in the field. Furthermore, we proposed a new multi-label classification model that outperforms the existing ones and achieves an accuracy of 97.83%. To ensure transparency and reproducibility, the source code for GuardLink is made openly accessible on GitHub.

The increase in the number of IoT devices invading both private and professional spaces opens the way for different cyberattacks. Facing such threats requires new approaches capable of reading the context of a given situation and acting accordingly to protect the users’ data and applications. Logical-based approaches can be harnessed in this case because of the semantic dimension they model and implement. In this paper, we make use of an existential rule-based knowledge base to model an IoT environment and detect anomalies as inconsistencies inside the obtained logical system. Accordingly, we first introduce an algorithm for knowledge base rewriting into a context-based knowledge base. Then, we detail our contextualized derivation algorithm for inconsistency detection in such a logical system.

Buildings are one of the biggest energy consumers and greenhouse gas producers. Technology could help reduce their environmental impact by deploying sensors to collect relevant data about the way energy is consumed, and with the aim to optimize it. For this sake, understanding building occupant's behavior and occupancy patterns can help minimize energy consumption while satisfying occupant's comfort. Indeed, occupants directly influence building appliances that consume energy, such as HVAC, ovens, hot water tanks, etc. In this paper, we aim at predicting occupants' movements among rooms and use the predicted movements to deduce room and space occupancy in the building. The latter is then used to preheat/pre-cool rooms. However, since prediction models are not always that accurate, it is possible to face situations where HVAC of some rooms are activated while these are empty or vice-versa, leading to either a waste of energy or a lack of occupant's comfort. To deal with this issue, we make use of sensors to detect real-time occupancy of building rooms and then correct the prediction when necessary. To achieve this, we developed a graph mining-based optimization approach that combines occupant behavior prediction and a real-time correction. We experimented our approach on simulated data and results showed that our model optimizes up to 39.09% of HVAC energy consumption, and provides up to 99.39% of occupants' comfort.

Vehicular cloud (VC) is a promising environment, where intelligent transport applications can be developed relying on mobile vehicles, which can be both cloud users and cloud service providers. It enables vehicles that have sufficient resources to act as mobile cloud servers by offering a variety of services to users' vehicles. In this context, to consume a cloud service on the move, a user vehicle must first identify the most stable vehicles, relative to his/her motion, which are able to provide the service, and then select the most suitable service according to his/her preferences, while both provider vehicles and their services are described by attributes or quality constraints. Therefore, we introduce a generic relative motion model, as a generic link stability metric, upon which vehicles can form a stable cloud, and we address the VC service selection by using linguistic quantifiers and fuzzy quantified propositions, to define our flexible quantified service selection (FQSS) scheme, which aggregates efficiently both user preferences and service constraints and ranks service providers from the most to the least satisfactory. To break ties among the top-ranked service providers, we make use of our parameters for ranking refinement, called least satisfactory proportion (lsp) and greatest satisfactory proportion (gsp). The simulation results show that our link stability achieves generic motion, by modeling a wider range of vehicle motion types, and our FQSS scheme allows a good successful service consumption rate while reducing latency.

Occupant behavior and space occupancy provide important information to controlling and optimizing energy use in buildings, especially when it comes to heating/cooling, where Heating, Ventilation, and Air Conditioning (HVAC) systems are in use. Besides, thermal comfort is mainly occupant behavior-dependent, based on his movements and space occupancy inside a building over the daytime. Traditional HVAC system functioning, based on turning OFF/ON of the system at the building level, without taking into account space occupancy, can lead to unnecessary heating/cooling of some rooms, which results in a waste of energy, or an under-heating/undercooling of the rooms leading to a lack of comfort. To optimize energy consumption and occupant comfort, we introduce in this paper a temporal graph-based approach for occupants' behavior modeling for energy consumption optimization at room level. Our approach combines a graph learning algorithm, a hierarchical clustering to identify frequent occupants movements within the optimal time interval decomposition of days, and a multi-objective problem resolution. We experimented our approach on a 4-week dataset of 4 occupants movements among office rooms. The first results showed that our model helps minimize energy consumption by up to 62.21% compared to conventional functioning of HVAC systems, and fulfills up to 94.02% of occupants' thermal comfort.

As the adoption of digital technologies expands, it becomes vital to build trust and confidence in the integrity of such technology. The SPIRIT project investigates the proof of concept of employing novel secure and privacy-ensuring techniques in services set-up in the Internet of Things (IoT) environment, aiming to increase the trust of users in IoTbased systems. The proposed system integrates three highly novel technology concepts developed by the consortium partners. Specifically, a technology, ermed ICMetrics, for deriving encryption keys directly from the operating characteristics of digital devices; secondly, a technology based on a contentbased signature of user data in order to ensure the integrity of sentdata upon arrival; a third technology, termed semantic firewall, which is able to allow or deny the transmission of data derived from an IoT device according to the information contained within the data and the information gathered about the requester.

Building energy consumption depends on many factors, such as occupant behavior and occupancy. Many works study building occupancy modeling and its impact on energy consumption, based on sensors, such as CO2, humidity, presence, etc., which are deployed within buildings and their surrounding areas. These sensors collect different types of data at a high frequency, which can be used to build datasets used in building predictive models. In this context, existing datasets have been empirically built without considering the relevant sensor types and the frequency of data collection for building occupancy modeling. Therefore, in this paper, we introduce a method to select the data collection period and the relevant sensors for building occupancy prediction model with satisfying accuracy. Our approach uses feature selection and machine learning classifier algorithms, which are applied to different data collection periods, starting from 1 minute to 60 minutes. The experiments, carried out on a real dataset, with 5 different machine learning classifiers show that it is possible to build an occupancy predictive model with Random Forest having an accuracy of at least 90%, by using 8 sensors collecting data at a 20-min interval, or 5 sensors collecting data at a 15-min interval.

Flexible querying exploits user preferences as pieces of information that help rank a set of alternatives from the most to the least satisfactory, based on the degrees of satisfaction of the criteria, describing the alternatives, to user preferences expressed by a user. Quantitative approaches for user preference evaluation and evaluation can perform such a ranking by defining total orders, based on a given aggregation function applied on satisfaction degrees to compute a global score. In this context, it becomes possible to end up with undistinguishable top-ranked alternatives, in the sense that they are equally scored. To break ties, we study in this paper a special type of user preferences involving linguistic quantifiers and fuzzy quantified propositions of the form "QX are A", where Q is a linguistic quantifier, X is a set of items and A is a fuzzy predicate. We define a new quantitative interpretation of the truth-value of fuzzy quantified propositions of the aforementioned form, in order to extract new useful information to be used in refining the ranking. To do so, two parameters, called least satisfactory proportion, denoted by lsp, and greatest satisfactory proportion, denoted by gsp, are defined as the lower bound and the upper bound, respectively, of the subset of the most satisfiable criteria, describing alternatives regarding a given set of user preferences. We show formally that lsp and gsp parameters can discriminate among tied top-ranked alternatives.

Vehicular Cloud (VC) is an emerging paradigm where vehicles having sufficient resources act as mobile cloud servers by offering a variety of services to user vehicles. To consume a cloud service on the move, a user vehicle must first identify the most stable vehicles, relatively to its motion, capable of providing the service, then select the most suitable service according to its preferences and service provider quality or constraints. In this paper, we introduce a link stability metric based on a generic relative motion model among vehicles to form a stable cloud and address vehicular cloud service selection by using linguistic quantifiers and fuzzy quantified propositions aggregating efficiently both user preferences and service constraints to rank service providers from the most to the least satisfactory. To break ties, we also define new parameters, called least satisfactory proportion (lsp) and greatest satisfactory proportion (gsp). Simulation results show that the link stability achieves generic motion and the selection approach allows a good successful service consumption rate while reducing latency.

We are in the era of information access in which a huge amount of text is extracted from scanned documents and made available digitally to be used in search processes. However, old or poorly scanned documents suffer from bad recognition, which leads to not only imperfect Optical Character Recognition (OCR), but to bad indexation and unattainable information, as well. To cope with the aforementioned issues, we introduce in this paper a lexicographical-based approach for Post-OCR correction applied to named entities. By combining lexicographically a contextual similarity and an edit distance, the approach builds a graph connecting similar named entities, in order to automatically correct the corresponding OCR processed text. We evaluated our approach on a generated dataset. The first results obtained showed that, despite the high level of degradation of the text, the approach succeeded in correcting more than a third of named entities without the need for any external knowledge.

International audience

International audience

Internet of Things (IoT)-based environments collect and generate huge amounts of data about users, their activities, and their surroundings, which can disclose some sensitive information and threat their privacy. Hence, user data collected and handled by IoT-based applications need to be exploited and secured in an appropriate way to protect personal data and user privacy. Therefore, we aim at designing a user-centric approach for user privacy protection based on two main blocks, namely (i) a habit-based approach for anomaly-based intrusion detection system, and (ii) semantic-based firewall for access control and communication security. We detail in this paper the design of the former block by introducing a generic algorithm for user habit learning as a pillar of our anomaly detection system, which is then instantiated by an intuitionistic fuzzy sets model to illustrate how it operates in a real world use-case.

Adaptive learning systems aim to personalize and adapt resources and learning strategies according to learners' knowledge acquisition and behavior. In this paper, knowledge acquisition is estimated by using traces learners left during their learning activities. Learner's traces considered are activity duration and number of attempts to solve a given problem, upon which we developed a trace-based evaluation model. The latter is integrated into a trace-based adaptation model made of ontological rules and reasoning mechanism to deliver adapted resources and personalized learning strategy, represented as learning paths, which are sequences of situations containing resources. The reasoning mechanism is implemented as a state-transition process governed by an adaptation algorithm we proposed.

Nowadays, smartphones and wearable devices are endowed with several sensors, which can harvest large quantities of data about urban areas (location information, pollution levels, etc.), going through a list of personal and surrounding contexts such as noise level, traffic awareness, to name a few. Exploiting this wealth of information provided by the crowd allows developers to design and build several applications over the so-called Mobile CrowdSensing, such as traffic regulation, environmental monitoring, tourism recommendation, etc. However, for this to be possible, many barriers still have to be overcome such as collecting, handling, structuring and representing the crowd data in a suitable way. In this paper, we propose a three-fold solution to the problem of data management in CrowdSensing systems. Firstly, we structure the collected data based on semantic ontologies. Secondly, we enrich the data based on a novel contextual awareness data interlinking. Finally, we refine recommendations with contexts, through taking into consideration meta-information interlinked to the main information of interest. We have implemented our model in a tourism recommendation application as a proof of concept. The experimental evaluation - which we carried out - has shown very promising results.

Ranking intuitionistic fuzzy alternatives has been widely studied by Szmidt and Kacprzyk in many work. The lake of a linear order amongst elements of intuitionistic fuzzy alternative sets, as stated in [1], oriented the researches to the definition of aggregation methods measuring the distance of each alternative to the best element of an intuitionistic fuzzy set. However, in some real applications such as raking possible items or alternatives according to positive and negative ratings, expressing respectively the satisfaction and dissatisfaction of some buyers in e-commerce applications, the distance may deliver some counter-intuitive results from the user's standpoint. Therefore, by considering intuitionistic fuzzy alternatives as particular fuzzy bipolar sets, we introduce in this paper an intuitionistic bipolar approach for alternative ranking, based on (i) two intuitionistic preference relations, namely intuitionistic more preferred than or equal to (denoted by equation) and intuitionistic less preferred than or equal to (denoted by equation), each of which is a linear order, which can be used to rank bipolar alternatives attached with both degrees of acceptance (membership) and rejection (non-membership), and on (ii) two algebraic operators called Intuitionistic minimum, denoted by Imin, and Intuitionistic maximum, denoted by Imax, to compute respectively the intersection and the union of intuitionistic fuzzy bipolar alternative sets.

We address the problem of explaining Boolean Conjunctive Query (BCQ) failure in the presence of inconsistency within the Ontology-Based Data Access (OBDA) setting, where inconsistency is handled by the intersection of closed repairs semantics (ICR) and the ontology is represented by Datalog+/− rules. Our proposal relies on an interactive and argumentative approach where the processes of explanation takes the form of a dialogue between the User and the Reasoner. We exploit the equivalence between argumentation and ICR-semantics to prove that the Reasoner can always provide an answer for user's questions.

Within the framework of the European project EcoBioCap (ECOefficient BIOdegradable Composite Advanced Packaging), aiming at conceiving the next generation of food packagings, we introduce an argumentation-based tool for management of conflicting viewpoints between preferences expressed by the involved parties (food and packaging industries, health and waste management etc.).

We introduce in this paper a quantitative preference based argumentation system relying on ASPIC argumentation framework [1] and fuzzy set theory. The knowledge base is fuzzified to allow agents expressing their expertise (premises and rules) attached with grades of importance in the unit interval. Arguments are then attached with a strength score aggregating the importance expressed on their premises and rules. Extensions, corresponding to subsets of consistent arguments, are also attached with forces computed based on their strong arguments. The forces are used then to rank extensions from the strongest to the weakest one, upon which decisions can be made. We have also shown that the strength preference relation defined over arguments is reasonable [2] and our fuzzy ASPIC argumentation system can be seen as a computationally efficient instantiation of the generic model of structured argumentation framework introduced in [2].

We introduce in this paper a new relational division operator based on a bipolar implication operator involving fuzzy bipolar relations. The considered bipolarity encompasses two kinds of bipolar conditions: the former is of type “and if possible”, and the latter is of type “or else”. This new division operator allows as to express a division of bipolar relations regardless of the nature of the dividend and the divisor (Boolean, fuzzy, bipolar, homogeneous, heterogeneous). We have also shown that the proposed relational division operator satisfies the bipolar quotient properties and can be an alternative to the already proposed operator in [1]-[3] which is based on the quantities involved in the division operation. The new proposed operator is aimed to be integrated into the bipolar SQLf language for flexible querying of relational databases.

The expression and the evaluation of complex user preferences in the context of distributed and heterogeneous information systems are tackled in this paper. Complex preferences are modeled by fuzzy bipolar conditions, which associate negative and positive conditions. Queries involving such conditions are called bipolar queries. In our case, such queries are addressed to information systems such as Web applications, built on several distributed and heterogeneous databases. This querying can lead to process huge volumes of data and can deliver massive responses, in which it is difficult to the user to distinguish the relevant answers from irrelevant ones. Semantic aspects make it possible to address this problem by providing a personalized data access method, so that only the most relevant data are targeted to evaluate queries. We introduce then in this paper a new approach for flexible querying of complex information systems that combines a reasoning mechanism (an ontology-based on the fuzzy bipolar DLR-Lite) with a bipolar relational language of a high expressivity (Bipolar SQLf language). The reasoning mechanism can also answer queries in approximative way, based on degrees expressing at which extent it is possible to substitute a concept in the query with other concepts, while still meaningful to the user.

Previously studied fuzzy bipolar conditions of type "and if possible" are made of a mandatory condition c and an optional condition w. They allow expressing complex preferences of a conjunctive nature. We define in this paper, a new kind of fuzzy bipolar conditions of the form "or else" which express complex preferences of a disjunctive nature. We show that the "or else" form can be used as a negation operator of the "and if possible" form and vice versa. We also show that these both forms are compatible and, therefore, fuzzy bipolar conditions of both types can be used together in the same bipolar query.

In this paper, we propose a personalized approach for flexible querying of information systems. This approach consists in the combination of the reasoning capabilities of the fuzzy DLR-Lite ontology and the expressivity of the SQLf language. The interpretation of the gradual inclusion (subsumption) axioms of the ontology is based on the Godel fuzzy implication. Its generalization to a tree of inclusions is also proposed. This tree and its property of propagation of degrees are the basic theoretical elements of our application, which consists in querying of a multimodal transport information system which is embedded in a mobile terminal characterized by limited storage and processing capabilities.