INRIA a CCSD electronic archive server
Not a member yet
122212 research outputs found
Sort by
Estradizione e diritti degli stranieri nell’Europa della fine dell Ottocento
No full textInternational audienceThis article examines the role of extradition and the rights of foreigners in Europe during the last quarter of the nineteenth century, showing how this seemingly technical legal practice was in fact at the centre of intense political, diplomatic, and ideological debates. From the 1870s onward, extradition became a crucial issue for international legal scholars, particularly within the Institut de Droit International (IDI), who sought to redefine its meaning in light of liberal principles, the protection of individual liberties, and state sovereignty.The author shows how liberal jurists attempted to transform extradition from a tool inherited from the Ancien Régime—often used to repress political opponents—into an act of justice governed by law and compatible with the right of asylum. The central issue of these debates concerned the definition of “political crime” and the limits within which a state could refuse to surrender a foreign national. These controversies intensified in a context of growing mobility, the nationalization of borders, and fears of subversion, particularly anarchism.Through an analysis of international debates and the French case, the article highlights the tensions between international law and state practices, demonstrating how, in the face of concerns for public order and security, states sometimes resorted to practices of expulsion that amounted to disguised extradition. Overall, the text sheds light on the dilemmas of late nineteenth-century liberal thought and the difficult balance between international cooperation, state sovereignty, and the protection of the fundamental rights of foreigners.Le présent article analyse le rôle de l’extradition et des droits des étrangers dans l’Europe du dernier quart du XIXe siècle, en montrant comment cette pratique juridique, en apparence technique, fut en réalité au cœur d’intenses débats politiques, diplomatiques et idéologiques. À partir des années 1870, l’extradition devint une question centrale pour les juristes internationalistes, en particulier au sein de l’Institut de droit international (IDI), qui cherchèrent à en redéfinir la signification à la lumière des principes libéraux, de la protection des libertés individuelles et de la souveraineté des États.L’auteur montre comment les juristes libéraux tentèrent de transformer l’extradition, héritée de l’Ancien Régime et souvent utilisée pour réprimer les opposants politiques, en un acte de justice encadré par le droit et compatible avec le droit d’asile. Le cœur des débats porta sur la définition du « crime politique » et sur les limites dans lesquelles un État pouvait refuser la remise d’un étranger. Ces controverses s’intensifièrent dans un contexte marqué par la mobilité croissante des personnes, la nationalisation des frontières et la peur du subversivisme, en particulier de l’anarchisme.À travers l’analyse des débats internationaux et du cas français, l’article met en évidence les tensions entre le droit international et les pratiques étatiques, montrant comment, face aux exigences de l’ordre public et de la sécurité, les États eurent parfois recours à des pratiques d’expulsion s’apparentant à une extradition déguisée. Dans l’ensemble, le texte éclaire les dilemmes de la raison libérale de la fin du siècle et le difficile équilibre entre coopération internationale, souveraineté étatique et protection des droits fondamentaux des étrangers.Il saggio analizza il ruolo dell’estradizione e dei diritti degli stranieri nell’Europa dell’ultimo quarto del XIX secolo, mettendo in luce come questa pratica giuridica, apparentemente tecnica, sia stata in realtà al centro di intensi dibattiti politici, diplomatici e ideologici. A partire dagli anni Settanta dell’Ottocento, l’estradizione divenne un tema cruciale per i giuristi internazionalisti, in particolare all’interno dell’Institut de Droit International (IDI), che cercarono di ridefinirne il significato alla luce dei principi liberali, della tutela delle libertà individuali e della sovranità degli Stati.L’autore mostra come i giuristi liberali tentassero di trasformare l’estradizione da strumento ereditato dall’Ancien Régime, spesso utilizzato per reprimere gli oppositori politici, in un atto di giustizia regolato dal diritto e compatibile con il diritto d’asilo. Il nodo centrale dei dibattiti riguardò la definizione di “reato politico” e i limiti entro cui uno Stato potesse rifiutare la consegna di uno straniero. Queste controversie si intensificarono nel contesto della crescente mobilità delle persone, della nazionalizzazione delle frontiere e della paura del sovversivismo, in particolare dell’anarchismo.Attraverso l’analisi dei dibattiti internazionali e del caso francese, il saggio evidenzia le tensioni tra diritto internazionale e pratiche statali, mostrando come, di fronte a esigenze di ordine pubblico e sicurezza, gli Stati ricorressero talvolta a pratiche di espulsione che sfioravano l’estradizione mascherata. Nel complesso, il testo mette in luce i dilemmi della ragione liberale di fine secolo e il difficile equilibrio tra cooperazione internazionale, sovranità statale e protezione dei diritti fondamentali degli stranieri
A New Tool to Find Lightweight (And, Xor) Implementations of Quadratic Vectorial Boolean Functions up to Dimension 9
No full textInternational audienceThe problem of finding a minimal circuit to implement a given function is one of the oldest in electronics. It is known to be NP-hard. Still, many tools exist to find sub-optimal circuits to implement a function. In electronics, such tools are known as synthesisers. However, these synthesisers aim to implement very large functions (a whole electronic chip). In cryptography, the focus is on small functions, hence the necessity for new dedicated tools for small functions. Several tools exist to implement small functions. They differ by their algorithmic approach (some are based on Depth-First-Search as introduced by Ullrich in 2011, some are based on SAT-solvers like the tool desgined by Stoffelen in 2016, some non-generic tools use subfield decomposition) and by their optimisation criteria (some optimise for circuit size, others for circuit depth, and some for side-channel-protected implementations). However, these tools are limited to functions operating on less than 5 bits, sometimes 6 bits for quadratic functions, or to very simple functions. The limitation lies in a high computing time. We propose a new tool (The tool is provided alongside the IEEE article with CodeOcean and at https://github.com/seduval/implem-quad-sbox) to implement quadratic functions up to 9 bits within AND-depth 1, minimising the number of AND gates. This tool is more time-efficient than previous ones, allowing to explore larger implementations than others on 6 bits or less and allows to reach larger sizes, up to 9 bits
A Logic-based Framework for Decoding Enthymemes in Argument Maps Involving Implicitness in Premises and Claims
No full textInternational audienceArgument mining is a natural language processing technology aimed at identifying the explicit premises and claims of arguments in text, and the support and attack relationships between them. To better understand, and automatically analyse, the argument maps that are output from argument mining, it would be desirable to instantiate the arguments in the argument map with logical arguments. However, most real-world arguments are enthymemes (i.e. some of the premises and/or claim are implicit), which need to be decoded (i.e. the implicit aspects need to be identified). A key challenge is to decode enthymemes so as to respect the support and attack relationships in the argument map. addressing the problem of identifying the missing premises and/or claim, and discerning the relationships between them. To address this, we present a novel framework, based on default logic, for representing arguments including enthymemes. We show how decoding an enthymeme means identifying the default rules that are implicit in the premises and claims. We then show how choosing a decoding of the enthymemes in an argument map can be formalized as an optimization problem, and that a solution can be obtained using MaxSAT solvers
Tolérance au fautes des Architectures matérielles pour algorithmes d'intelligence artificielle
No full textNeural networks are widely used across various domains and are increasingly deployed in critical environments such as aerospace, healthcare, and autonomous driving. Their integration into embedded systems poses challenges related to energy consumption, limited hardware resources, and vulnerability to faults, including bit-flips caused by radiation, manufacturing defects, or component aging. This thesis proposes a method for evaluating the robustness of neural networks based on statistical fault injection, implemented in the SFI4NN tool, which allowsassessing the impact of perturbations without exhaustive exploration. A key feature of this approach is the analysis of fault directionality, showing that bit-flips moving values away from zero are the most critical, while early layers and the most significant bits are particularly sensitive. Based on these findings, several hardware protection mechanisms were developed, including HTAG for floating-point formats, VANDOR for fixed-point representations, and TVU, a hybrid approach, which exploit this asymmetry to enhance reliability while limiting hardware cost. Overall, this work highlights the importance of considering fault directionality to design more reliable embedded neural networks adapted to the constraints of critical environments.Les réseaux de neurones, utilisés dans de nombreux domaines, trouvent également leur place dans des environnements critiques tels que l’aérospatial, le médical ou la conduite autonome. Leur déploiement sur des systèmes embarqués pose des défis liés à la consommation énergétique, aux ressources matérielles limitées et à leur vulnérabilité aux perturbations, notamment les inversions de bits causées par les radiations, les défauts de fabrication ou le vieillissement des composants. Cette thèse propose une méthode d’évaluation de la robustesse des réseaux de neurones basée sur l’injection statistique de fautes, mise en œuvre dans l’outil SFI4NN, permettant de mesurer l’impact des perturbations sans exploration exhaustive. Une originalité de cette approche est l’analyse de la directionnalité des fautes, montrant que les inversions éloignant les valeurs de zéro sont les plus critiques, tandis que certaines couches et bits les plus significatifs sont sensibles.Plusieurs mécanismes matériels de protection ont été développés, tels que HTAG pour les formats flottants, VANDOR pour les représentations fixes et TVU, une approche hybride, qui exploitent cette asymétrie pour améliorer la fiabilité tout en limitant le coût matériel. Ces travaux soulignent l’importance de considérer la directionnalité des fautes pour concevoir des réseaux embarqués fiables et adaptés aux environnements critiques
Master classes of the tenth international brain–computer interface meeting: showcasing the research of BCI trainees
No full textInternational audienceThe Tenth International brain–computer interface (BCI) meeting was held June 6–9, 2023, in the Sonian Forest in Brussels, Belgium. At that meeting, 21 master classes, organized by the BCI Society’s Postdoc & Student Committee, supported the Society’s goal of fostering learning opportunities and meaningful interactions for trainees in BCI-related fields. Master classes provide an informal environment where senior researchers can give constructive feedback to the trainee on their chosen and specific pursuit. The topics of the master classes span the whole gamut of BCI research and techniques. These include data acquisition, neural decoding and analysis, invasive and noninvasive stimulation, and ethical and transitional considerations. Additionally, master classes spotlight innovations in BCI research. Herein, we discuss what was presented within the master classes by highlighting each trainee and expert researcher, providing relevant background information and results from each presentation, and summarizing discussion and references for further study
BATT2GRAPH: A Hybrid CNN-LSTM and Temporal Graph-Based Approach for Lithium-Ion Battery SOH Prediction and Anomaly Detection
No full textInternational audienceThe rapid adoption of electric vehicles (EVs) underscores the growing need for reliable battery health monitoring systems to ensure safety, optimize performance, and extend operational lifespan. In this paper, we introduce BATT2GRAPH, a novel approach that combines a temporal graph-based representation with a CNN-LSTM predictive model for accurate State-of-Health (SOH) estimation and anomaly detection in lithium-ion batteries (LIBs). On one hand, BATT2GRAPH constructs a temporal property graph using Neo4j to store enriched charge-discharge cycles with both raw time-series data and aggregated statistical indicators, enabling interpretable SOH monitoring and anomaly detection through expressive Cypher queries. On the other hand, a hybrid CNN-LSTM model is trained on this data to capture fine-grained variations and long-term degradation trends. Extensive experiments on the Stanford-MIT battery aging dataset demonstrate that our approach consistently outperforms existing baselines across multiple evaluation metrics
Passive Neuroart BCI for Health: A Perspective
No full textInternational audienceEngaging with art can be beneficial for health and well-being [1]. Neural correlates of art perception related to attentional, affective and hedonic processes are already used in Brain-Computer-Interfaces (BCIs) [2]. Therefore, we think that positive effects of aesthetic experience (AE) can be optimized by BCI. This work elaborates on potential health applications combining neuroart and passive BCI for neuroadaptive art presentation. Finally, we offer perspectives on new methods to further the development of such applications
Resource-Efficient Sensor Fusion at the Edge via System-Wide Dynamic Gated Neural Networks
No full textInternational audienceNext-generation mobile systems will support multiple AI-based applications, each leveraging heterogeneous sensors and data sources through deep neural network (DNN) architectures collaboratively executed within the network. In this context, to minimize the cost of the AI inference task subject to requirements on latency, quality, and -cruciallyreliability of the inference process, it is vital to optimize (i) the set of sensors/data sources and (ii) the DNN architecture, (iii) the network nodes executing sections of the DNN, and (iv) the resources to use. To achieve these goals, we leverage dynamic gated neural networks with branches, and propose a novel algorithmic strategy called Quantile-constrained Inference (QIC), based upon quantile-Constrained policy optimization. QIC makes joint, highquality, swift decisions on all the above aspects of the system, with the aim to minimize inference energy cost. We remark that this is the first contribution connecting gated dynamic DNNs with infrastructure-level decision making. We evaluate QIC using a dynamic gated DNN with stems and branches for optimal sensor fusion and inference, trained on the RADIATE dataset offering Radar, LiDAR, and Camera data, and real-world wireless measurements. Our results confirm that QIC closely matches the optimum and outperforms existing approaches in reducing energy consumption (compute, communication, and total) and application requirements failure by over 70%.</div
Results of CMatch in OAEI 2025
No full textInternational audienceThis paper presents CMatch (Complex Matcher), an LLM-based ontology matching approach designed for the Complex Track of the Ontology Alignment Evaluation Initiative (OAEI) 2025. CMatch addresses two core challenges in complex ontology matching: the combinatorial explosion of candidate subgraph pairs and the generation of expressive, logic-based correspondences (e.g., n:m correspondences involving class unions or property compositions)
Combining LLMs-based Conversational Agents and Ontologies for Open Data Research
No full textInternational audienceOpen Science has significantly increased the availability of heterogeneous scientific datasets. However, these datasets are often described with poor metadata, which makes it difficult to identify data relevant to a specific user's needs. The pertinent data sets may be hard to find when described with poor metadata, or if users' needs are expressed using a different vocabulary. This paper proposes an approach that combines semantically enriched metadata with LLM-based agents that interpret natural language queries to manage the gap between users' needs and dataset descriptions, and to support the retrieval of relevant datasets. It enables the extraction and refinement of user needs, as well as the generation of justifications for the retrieved results. To assess the performance of the proposed system, an evaluation was conducted across multiple Earth Observation (EO) data request scenarios. Four LLM agents have been evaluated (LLaMA 3.3 70B, Mistral Saba 24B, Deepseek-R1, and Qwen 32B) using metrics such as answer relevancy, contextual precision, recall, and faithfulness. The results, conducted with the Deepeval library with the LLaMA 3 8B model, show relatively high scores for answer relevance and contextual precision, especially with the LLaMA and Deepseek-R1 models