Search

Your search keyword '"Lemesle, Augustin"' showing total 15 results
Start Over Author "Lemesle, Augustin"
15 results on '"Lemesle, Augustin"'

1. Neural Network Verification is a Programming Language Challenge

Author

Cordeiro, Lucas C., Daggitt, Matthew L., Girard-Satabin, Julien, Isac, Omri, Johnson, Taylor T., Katz, Guy, Komendantskaya, Ekaterina, Lemesle, Augustin, Manino, Edoardo, Šinkarovs, Artjoms, and Wu, Haoze

Subjects
Computer Science - Programming Languages, Computer Science - Machine Learning, Computer Science - Logic in Computer Science
Abstract

Neural network verification is a new and rapidly developing field of research. So far, the main priority has been establishing efficient verification algorithms and tools, while proper support from the programming language perspective has been considered secondary or unimportant. Yet, there is mounting evidence that insights from the programming language community may make a difference in the future development of this domain. In this paper, we formulate neural network verification challenges as programming language challenges and suggest possible future solutions., Comment: Accepted at ESOP 2025, European Symposium on Programming Languages

Published
2025

2. Neural Network Verification with PyRAT

Author

Lemesle, Augustin, Lehmann, Julien, and Gall, Tristan Le

Subjects
Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

As AI systems are becoming more and more popular and used in various critical domains (health, transport, energy, ...), the need to provide guarantees and trust of their safety is undeniable. To this end, we present PyRAT, a tool based on abstract interpretation to verify the safety and the robustness of neural networks. In this paper, we describe the different abstractions used by PyRAT to find the reachable states of a neural network starting from its input as well as the main features of the tool to provide fast and accurate analysis of neural networks. PyRAT has already been used in several collaborations to ensure safety guarantees, with its second place at the VNN-Comp 2024 showcasing its performance.

Published
2024

3. CAISAR: A platform for Characterizing Artificial Intelligence Safety and Robustness

Author

Girard-Satabin, Julien, Alberti, Michele, Bobot, François, Chihani, Zakaria, and Lemesle, Augustin

Subjects
Computer Science - Artificial Intelligence, Computer Science - Logic in Computer Science, Computer Science - Neural and Evolutionary Computing, Computer Science - Software Engineering
Abstract

We present CAISAR, an open-source platform under active development for the characterization of AI systems' robustness and safety. CAISAR provides a unified entry point for defining verification problems by using WhyML, the mature and expressive language of the Why3 verification platform. Moreover, CAISAR orchestrates and composes state-of-the-art machine learning verification tools which, individually, are not able to efficiently handle all problems but, collectively, can cover a growing number of properties. Our aim is to assist, on the one hand, the V\&V process by reducing the burden of choosing the methodology tailored to a given verification problem, and on the other hand the tools developers by factorizing useful features-visualization, report generation, property description-in one platform. CAISAR will soon be available at https://git.frama-c.com/pub/caisar.

Published
2022

4. AIMOS: Metamorphic Testing of AI - An Industrial Application

Author

Lemesle, Augustin, Varasse, Aymeric, Chihani, Zakaria, Tachet, Dominique, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Guiochet, Jérémie, editor, Tonetta, Stefano, editor, Schoitsch, Erwin, editor, Roy, Matthieu, editor, and Bitsch, Friedemann, editor

Published
2023
Full Text
View/download PDF

6. Introducing the TRUMPET project: TRUstworthy Multi-site Privacy Enhancing Technologies

Author

Pedrouzo-Ulloa, Alberto, primary, Ramon, Jan, additional, Péerez-González, Fernando, additional, Lilova, Siyanna, additional, Duflot, Patrick, additional, Chihani, Zakaria, additional, Gentili, Nicola, additional, Ulivi, Paola, additional, Hoque, Mohammad Ashadul, additional, Mukammel, Twaha, additional, Pritzker, Zeev, additional, Lemesle, Augustin, additional, Loureiro-Acuña, Jaime, additional, Martínez, Xavier, additional, and Jiménez-Balsa, Gonzalo, additional

Published
2023
Full Text
View/download PDF

7. Introducing the TRUMPET project: TRUstworthy Multi-site Privacy Enhancing Technologies

Author

Pedrouzo-Ulloa, Alberto, Ramon, Jan, Duflot, Patrick, Pérez-González, Fernando, Lilova, Siyanna, Chihani, Zakaria, Gentili, Nicola, Ulivi, Paola, Hoque, Mohammad Ashadul, Mukammel, Twaha, Pritzker, Zeev, Lemesle, Augustin, Loureiro-Acuña, Jaime, Martı́nez, Xavier, Jiménez-Balsa, Gonzalo, Universidade de Vigo, Machine Learning in Information Networks (MAGNET), Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Centre Hospitalier Universitaire de Liège (CHU-Liège), Timelex, Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Istituto Scientifico Romagnolo per lo Studio e la Cura dei Tumori (IRST) IRCCS, Technovative Solutions, Arteevo Technologies, Centro Tecnoloxico de Telecomunicacions de Galicia (Gradiant), and European Project: 101070038,TRUMPET

Subjects
Privacy Metrics, Patient Data Privacy, AI, Federated Learning Privacy Metrics Privacy Enhancing Technologies General Data Protection Regulation Clinical Cancer Research Patient Data Privacy, Healthcare, Clinical Cancer Research, [INFO]Computer Science [cs], Privacy Enhancing Technologies, Federated Learning, General Data Protection Regulation
Abstract

International audience; This paper is an overview of the EU-funded project TRUMPET (https://trumpetproject.eu/), and gives an outline of its scope and main technical aspects and objectives. In recent years, Federated Learning has emerged as a revolutionary privacy-enhancing technology. However, further research has cast a shadow of doubt on its strength for privacy protection. The goal of TRUMPET is to research and develop novel privacy enhancement methods for Federated Learning, and to deliver a highly scalable Federated AI service platform for researchers, that will enable AI-powered studies of siloed, multi-site, crossdomain, cross-border European datasets with privacy guarantees that follow the requirements of GDPR. The generic TRUMPET platform will be piloted, demonstrated and validated in the specific use case of European cancer hospitals, allowing researchers and policymakers to extract AI-driven insights from previously inaccessible cross-border, cross-organization cancer data, while ensuring the patients' privacy.

Published
2023

8. ReCIPH: Relational Coefficients for Input Partitioning Heuristic

Author

Durand, Serge, Lemesle, Augustin, Chihani, Zakaria, Urban, Caterina, Terrier, François, Analyse Statique par Interprétation Abstraite (ANTIQUE), Département d'informatique - ENS Paris (DI-ENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria), Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Département Ingénierie Logiciels et Systèmes (DILS), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS), European Project: 830892,SPARTA(2019), European Project: 826276,CPS4EU(2019), Urban, Caterina, Strategic programs for advanced research and technology in Europe - SPARTA - 2019-01-01 - 2022-01-01 - 830892 - VALID, and Applying CPS technologies in modern manufacturing - CPS4EU - 2019-07-01 - 2022-06-30 - 826276 - VALID

Subjects
[INFO.INFO-PL]Computer Science [cs]/Programming Languages [cs.PL], [INFO.INFO-PL] Computer Science [cs]/Programming Languages [cs.PL]
Abstract

International audience; With the rapidly advancing improvements to the already successful Deep Learning artifacts, Neural Networks (NN) are poised to permeate a growing number of everyday applications, including ones where safety is paramount and, therefore, formal guarantees are a precious commodity. To this end, Formal Methods, a long-standing, mathematically-inspired field of research saw an effervescent outgrowth targeting NN and advancing almost as rapidly as AI itself. Without a doubt, the most challenging problem facing this new research direction is the scalability to the evergrowing NN models. This paper stems from this need and introduces Relational Coefficients for Input partitioning Heuristic (ReCIPH), accelerating NN analysis. Extensive experimentation is supplied to assert the added value to two different solvers handling several models and properties (coming, in part, from two industrial use-cases).

Published
2022

9. D3.4 ���ENSURESEC Architecture

Author

Francaviglia, Giuseppe, Sousa, Luís, Theodoropoulos, Christos, Diaz, Rodrigo, Kozic, Rafal, Milánkovich, Ákos, Lukács, Dávid, Dimakopoulos, Nikos, Nati, Michele, Signoles, Julien, Lemesle, Augustin, Gilga. Razvan, Daskalakis, Emmanouil, Khan, Muhammad Taimoor, and Rademacher, Rebecca

Subjects
Integration Plan, H2020, Logical Architecture, Conceptual Data Model, Data Flow
Abstract

This Report presents the results of Task 3.4 –System architecture and integration planning. The detailed technical specification of the components, the logical architecture, the conceptual data model and data flow, the integration plan and finally, guidelines for testing, usability and pilot adoption are presented. &nbsp

Published
2021
Full Text
View/download PDF

10. Confiance.ai, avancées scientifiques et technologiques.

Author

ADEDJOUMA, Morayo, ALIX, Christophe, BONHOMME, Yannick, BRAUNSCHWEIG, Bertrand, BRAUD, Raphaël, CANTAT, Loïc, CHALE-GONGORA, Hugo Guillermo, CHIHANI, Zakaria, DEJEAN, Philippe, DELLINGER, Flora, GELIN, Rodolphe, LOESCH, Angélique, LEMESLE, Augustin, MATTIOLI, Juliette, NICOLAS, Yves, ROBERT, Boris, TAHIRI, Yassine, TSCHIRHART, Fabien, Wouters, Thomas, and Yelloz, Jacques

Published
2023

Catalog

Books, media, physical & digital resources
See catalog results