{"id":141,"date":"2025-03-11T22:29:04","date_gmt":"2025-03-11T21:29:04","guid":{"rendered":"https:\/\/project.inria.fr\/saif\/?page_id=141"},"modified":"2025-03-11T22:29:05","modified_gmt":"2025-03-11T21:29:05","slug":"publications","status":"publish","type":"page","link":"https:\/\/project.inria.fr\/saif\/publications\/","title":{"rendered":"Publications"},"content":{"rendered":"<p><strong><code><div id=\"wphal-content\"><div id=\"meta\">\n        <div class=\"display\" id=\"wphal-contact\" style=\"display: none\">\n            <h3 class=\"wphal-titre\">Contact<\/h3>\n\n            <ul id=\"wphal-cont\" style=\"list-style-type: none\"><\/ul>\n        <\/div>\n        <div class=\"display\" id=\"wphal-disciplines\" style=\"display: none\">\n            <h3 class=\"wphal-titre\">Domains<\/h3><\/div>\n        <div class=\"display\" id=\"wphal-keywords\" style=\"display: none\">\n            <h3 class=\"wphal-titre\">Keywords<\/h3><\/div>\n        <div class=\"display\" id=\"wphal-auteurs\" style=\"display: none\">\n            <h3 class=\"wphal-titre\">Authors<\/h3><\/div>\n        <div class=\"display\" id=\"wphal-affiliated\" style=\"display: none\">\n            <h3 class=\"wphal-titre\">Affiliated authors<\/h3><\/div>\n        <div class=\"display\" id=\"wphal-revues\" style=\"display: none\">\n            <h3 class=\"wphal-titre\">Journals<\/h3><\/div>\n        <div class=\"display\" id=\"wphal-annees\" style=\"display: none\">\n            <h3 class=\"wphal-titre\">Year of production<\/h3><\/div>\n        <div class=\"display\" id=\"wphal-insts\" style=\"display: none\">\n            <h3 class=\"wphal-titre\">Institutions<\/h3><\/div>\n       <div class=\"display\" id=\"wphal-labs\" style=\"display: none\">\n            <h3 class=\"wphal-titre\">Laboratories<\/h3><\/div>\n       <div class=\"display\" id=\"wphal-depts\" style=\"display: none\">\n            <h3 class=\"wphal-titre\">Departments<\/h3><\/div>\n       <div class=\"display\" id=\"wphal-equipes\" style=\"display: none\">\n            <h3 class=\"wphal-titre\">Research team<\/h3><\/div>\n    <div class=\"display\" id=\"publications\"><div class=\"counter-doc\"><span class=\"wphal-nbtot\">30 <\/span>documents<\/div><br><div class=\"grp-div\"><h3 class=\"wphal-titre-groupe\">Journal articles<span class=\"wphal-nbmetadata\" style=\"margin-left:10px\">5 document<\/span><\/h3><div class=\"grp-content\"><ul><li>Matthias F\u00fcgger, Thomas Nowak, Kerian Thuillier. Distributed computing inspired by biology. <i>Seminars in Cell and Developmental Biology<\/i>, 2025, 175, pp.103666. <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1016\/j.semcdb.2025.103666\">&#x27E8;10.1016\/j.semcdb.2025.103666&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-05375376v1\">&#x27E8;hal-05375376&#x27E9;<\/a><\/li><li>Alessandro De Palma, Serge Durand, Zakaria Chihani, Caterina Urban. On Using Certified Training towards Empirical Robustness. <i>Transactions on Machine Learning Research Journal<\/i>, 2025. <a target=\"_blank\" href=\"https:\/\/inria.hal.science\/hal-05042448v1\">&#x27E8;hal-05042448&#x27E9;<\/a><\/li><li>Th\u00e9o Matricon, Nathana\u00ebl Fijalkow, Guillaume Lagarde. EcoSearch: A Constant-Delay Best-First Search Algorithm for Program Synthesis. <i>Proceedings (AAAI Artificial Intelligence and Interactive Digital Entertainment Conference)<\/i>, In press, <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.48550\/arXiv.2412.17330\">&#x27E8;10.48550\/arXiv.2412.17330&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-04901266v1\">&#x27E8;hal-04901266&#x27E9;<\/a><\/li><li>Marco Campion, Mila Dalla Preda, Roberto Giacobazzi, Caterina Urban. A Logic for the Imprecision of Abstract Interpretations. <i>Proceedings of the ACM on Programming Languages<\/i>, In press, POPL 2026, <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1145\/3776707\">&#x27E8;10.1145\/3776707&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-05402142v1\">&#x27E8;hal-05402142&#x27E9;<\/a><\/li><li>Marco Campion, Mila Dalla Preda, Roberto Giacobazzi, Caterina Urban. Monotonicity and the Precision of Program Analysis. <i>Proceedings of the ACM on Programming Languages<\/i>, 2024, 8 (POPL), pp.1629-1662. <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1145\/3632897\">&#x27E8;10.1145\/3632897&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/inria.hal.science\/hal-04423578v1\">&#x27E8;hal-04423578&#x27E9;<\/a><\/li><\/ul><\/div><\/div><br><div class=\"grp-div\"><h3 class=\"wphal-titre-groupe\">Conference papers<span class=\"wphal-nbmetadata\" style=\"margin-left:10px\">20 document<\/span><\/h3><div class=\"grp-content\"><ul><li>Marco Campion, Isabella Mastroeni, Michele Pasqua, Caterina Urban. Abstract Lipschitz Continuity: Combining Semantic and Quantitative Approximations. <i>Foundations of Software Science and Computation Structures (FoSSaCS 2026)<\/i>, Apr 2026, Turin (IT), Italy. pp.153-177, <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1007\/978-3-032-22730-0_8\">&#x27E8;10.1007\/978-3-032-22730-0_8&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/inria.hal.science\/hal-04935306v4\">&#x27E8;hal-04935306v4&#x27E9;<\/a><\/li><li>Rapha\u00ebl Faure, Alain Finkel. Automating Linguistic Frameworks with LLMs: An Approach to Analyze Personal Narratives. <i>The 3rd International Conference on Foundation and Large Language Models (FLLM2025)<\/i>, Nov 2025, Vienne, Austria. pp.23-30, <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1109\/FLLM67465.2025.11390984\">&#x27E8;10.1109\/FLLM67465.2025.11390984&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-05364834v1\">&#x27E8;hal-05364834&#x27E9;<\/a><\/li><li>Gustave Cortal, Alain Finkel. Formalizing Style in Personal Narratives. <i>Empirical Methods in Natural Language Processing (EMNLP 2025)<\/i>, Nov 2025, Suzhou, China. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-05261564v3\">&#x27E8;hal-05261564v3&#x27E9;<\/a><\/li><li>Yuke Liao, Blaise Genest, Kuldeep Meel, Shaan Aryaman. Solution-Aware Vs Global ReLU Selection: Partial MILP Strikes Back for\u00a0DNN Verification. <i>23rd International Symposium Automated Technology for Verification and Analysis (ATVA 2025)<\/i>, Oct 2025, Bangalore, India. pp.299-320, <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1007\/978-3-032-08707-2_14\">&#x27E8;10.1007\/978-3-032-08707-2_14&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-05384407v1\">&#x27E8;hal-05384407&#x27E9;<\/a><\/li><li>Dorin Doncenco, Julien Girard-Satabin, Romain Xu-Darme, Zakaria Chihani. A dive into formal explainable attributions for image classification. <i>European Conference on Artificial Inteligence 2025<\/i>, Oct 2025, Bologna, Italy. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-05219606v1\">&#x27E8;hal-05219606&#x27E9;<\/a><\/li><li>Guannan Wei, Zhuo Zhang, Caterina Urban. Hallucination-Resilient LLM-Driven Sound and Tunable Static Analysis. <i>LMPL 2025 - 1st International Workshop on Language Models and Programming Languages<\/i>, Oct 2025, Singapore, Singapore. <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1145\/3759425.3763378\">&#x27E8;10.1145\/3759425.3763378&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/inria.hal.science\/hal-05296479v1\">&#x27E8;hal-05296479&#x27E9;<\/a><\/li><li>Marco Campion, Isabella Mastroeni, Caterina Urban. Relating Distances and Abstractions: An Abstract Interpretation Perspective. <i>SAS 2025 - 32nd Static Analysis Symposium<\/i>, Oct 2025, Singapore, Singapore. <a target=\"_blank\" href=\"https:\/\/inria.hal.science\/hal-05207631v1\">&#x27E8;hal-05207631&#x27E9;<\/a><\/li><li>Augustin Lemesle, Julien Lehmann, Tristan Le Gall, Hichem-Zakaria Chihani. Verifying neural networks with PyRAT. <i>SAS 2025 - 32nd Static Analysis Symposium<\/i>, Oct 2025, Singapour, Singapore. pp.1 1-33, <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1007\/978-3-032-07106-4_2\">&#x27E8;10.1007\/978-3-032-07106-4_2&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/cea.hal.science\/cea-05394082v1\">&#x27E8;cea-05394082&#x27E9;<\/a><\/li><li>Raghda El Shehaby, Matthias F\u00fcgger, Florian Huemer, Andreas Steininger. Investigating the Effects of Permanent Faults in QDI Circuits: A Formal Perspective. <i>2025 29th IEEE International Symposium on Asynchronous Circuits and Systems (ASYNC)<\/i>, May 2025, Portland, United States. pp.142-150, <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1109\/ASYNC65240.2025.00027\">&#x27E8;10.1109\/ASYNC65240.2025.00027&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-05187822v1\">&#x27E8;hal-05187822&#x27E9;<\/a><\/li><li>Harleen Hanspal, Alessandro De Palma, Alessio Lomuscio. Robustness to Perturbations in the Frequency Domain: Neural Network Verification and Certified Training. <i>WACV 2025 - Workshop on Out-of-Label Hazards in Autonomous Driving<\/i>, May 2025, Tucson, Arizona, United States. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-05330224v1\">&#x27E8;hal-05330224&#x27E9;<\/a><\/li><li>Marius Belly, Nathana\u00ebl Fijalkow, Hugo Gimbert, Florian Horn, Guillermo Alberto P\u00e9rez, et al.. Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives. <i>39th AAAI Conference on Artificial Intelligence (AAAI-25)<\/i>, Feb 2025, Philadelphie, PA, United States. pp.26454-26462, <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1609\/aaai.v39i25.34845\">&#x27E8;10.1609\/aaai.v39i25.34845&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-04797702v4\">&#x27E8;hal-04797702v4&#x27E9;<\/a><\/li><li>Zhuofan Xu, Benedikt Bollig, Matthias F\u00fcgger, Thomas Nowak. Permutation Equivariant Deep Reinforcement Learning for Multi-Armed Bandit. <i>36th IEEE International Conference on Tools with Artificial Intelligence (ICTAI)<\/i>, Oct 2024, Herndon, United States. <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1109\/ICTAI62512.2024.00140\">&#x27E8;10.1109\/ICTAI62512.2024.00140&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-04787072v1\">&#x27E8;hal-04787072&#x27E9;<\/a><\/li><li>Denis Mazzucato, Marco Campion, Caterina Urban. Quantitative Static Timing Analysis. <i>31st Static Analysis Symposium (SAS 2024)<\/i>, Roberto Giacobazzi; Alessandra Gorla; Marco Campion, Oct 2024, Pasadena, CA, United States. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-04669723v1\">&#x27E8;hal-04669723&#x27E9;<\/a><\/li><li>Ben Batten, Yang Zheng, Alessandro De Palma, Panagiotis Kouvaros, Alessio Lomuscio. Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisation. <i>ECAI 2024 - European Conference on Artificial Intelligence<\/i>, Oct 2024, Santiago de Compostela, Spain. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-04727955v1\">&#x27E8;hal-04727955&#x27E9;<\/a><\/li><li>Romain Xu-Darme, Aymeric Varasse, Alban Grastien, Julien Girard, Zakaria Chihani. CaBRNet, an open-source library for developing and evaluating Case-Based Reasoning Models. <i>xAI 2024 - The 2nd World Conference on eXplainable Artificial Intelligence<\/i>, Jul 2024, La valette, Malta. pp.TBD. <a target=\"_blank\" href=\"https:\/\/cea.hal.science\/cea-04688217v2\">&#x27E8;cea-04688217v2&#x27E9;<\/a><\/li><li>Denis Mazzucato, Marco Campion, Caterina Urban. Quantitative Input Usage Static Analysis. <i>NASA Formal Methods 2024<\/i>, Jun 2024, Moffett Field (CA), United States. pp.79-98, <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1007\/978-3-031-60698-4_5\">&#x27E8;10.1007\/978-3-031-60698-4_5&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-04339001v3\">&#x27E8;hal-04339001v3&#x27E9;<\/a><\/li><li>Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham, M Pawan Kumar, Robert Stanforth, et al.. Expressive Losses for Verified Robustness via Convex Combinations. <i>ICLR 2024 - International Conference on Learning Representations<\/i>, May 2024, Vienna, Austria. <a target=\"_blank\" href=\"https:\/\/inria.hal.science\/hal-04511820v1\">&#x27E8;hal-04511820&#x27E9;<\/a><\/li><li>Mehdi Zadem, Sergio Mover, Sergio Mover, Sao Mai Nguyen. Reconciling Spatial and Temporal Abstractions for Goal Representation. <i>ICLR 2024: Twelfth International Conference on Learning Representations<\/i>, May 2024, Vienna, Austria. <a target=\"_blank\" href=\"https:\/\/inria.hal.science\/hal-04629549v1\">&#x27E8;hal-04629549&#x27E9;<\/a><\/li><li>Abhinandan Pal, Francesco Ranzato, Caterina Urban, Marco Zanella. Abstract Interpretation-Based Feature Importance for\u00a0Support Vector Machines. <i>25th International Conference on Verification, Model Checking, and Abstract Interpretation (VMCAI 2024)<\/i>, Jan 2024, London, United Kingdom. pp.27-49, <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1007\/978-3-031-50524-9_2\">&#x27E8;10.1007\/978-3-031-50524-9_2&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/inria.hal.science\/hal-04378817v1\">&#x27E8;hal-04378817&#x27E9;<\/a><\/li><li>L\u00e9o Henry, Blaise Genest, Alexandre Drewery. Reinforcement Planning for effective \u03b5-optimal policies in dense time with discontinuities. <i>43rd IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science<\/i>, Dec 2023, hyderabad, India. <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.4230\/LIPIcs\">&#x27E8;10.4230\/LIPIcs&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-04280462v1\">&#x27E8;hal-04280462&#x27E9;<\/a><\/li><\/ul><\/div><\/div><br><div class=\"grp-div\"><h3 class=\"wphal-titre-groupe\">Proceedings<span class=\"wphal-nbmetadata\" style=\"margin-left:10px\">1 document<\/span><\/h3><div class=\"grp-content\"><ul><li>Eric Goubault, Sylvie Putot. A Zonotopic Dempster-Shafer Approach to the Quantitative Verification of Neural Networks. <i>International Symposium on Formal Methods, FM 2024<\/i>, 14933, Springer Nature Switzerland, pp.324-342, 2025, Lecture Notes in Computer Science, <a target=\"_blank\" href=\"https:\/\/dx.doi.org\/10.1007\/978-3-031-71162-6_17\">&#x27E8;10.1007\/978-3-031-71162-6_17&#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-04546350v2\">&#x27E8;hal-04546350v2&#x27E9;<\/a><\/li><\/ul><\/div><\/div><br><div class=\"grp-div\"><h3 class=\"wphal-titre-groupe\">Preprints, Working Papers<span class=\"wphal-nbmetadata\" style=\"margin-left:10px\">2 document<\/span><\/h3><div class=\"grp-content\"><ul><li>Michele Alberti, Fran\u00e7ois Bobot, Julien Girard-Satabin, Alban Grastien, Aymeric Varasse, et al.. The CAISAR Platform: Extending the Reach of Machine Learning Specification and Verification. 2026. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-05086899v2\">&#x27E8;hal-05086899v2&#x27E9;<\/a><\/li><li>Benedikt Bollig, Matthias F\u00fcgger, Thomas Nowak. A Framework for Streaming Event-Log Prediction in Business Processes. 2025. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-04866045v1\">&#x27E8;hal-04866045&#x27E9;<\/a><\/li><\/ul><\/div><\/div><br><div class=\"grp-div\"><h3 class=\"wphal-titre-groupe\">Reports<span class=\"wphal-nbmetadata\" style=\"margin-left:10px\">1 document<\/span><\/h3><div class=\"grp-content\"><ul><li>Vaishak Belle, Michael Benedikt, Dana Drachsler-Cohen, Daniel Neider, Tom Yuviler, et al.. Logic and Neural Networks (Dagstuhl Seminar 25061). Dagstuhl. 2025. <a target=\"_blank\" href=\"https:\/\/hal.science\/hal-05311341v1\">&#x27E8;hal-05311341&#x27E9;<\/a><\/li><\/ul><\/div><\/div><br><div class=\"grp-div\"><h3 class=\"wphal-titre-groupe\">Theses<span class=\"wphal-nbmetadata\" style=\"margin-left:10px\">1 document<\/span><\/h3><div class=\"grp-content\"><ul><li>Denis Mazzucato. Static Analysis by Abstract Interpretation of Quantitative Program Properties. Computer Science [cs]. \u00c9cole Normale Sup\u00e9rieure, 2024. English. <a target=\"_blank\" href=\"https:\/\/www.theses.fr\/\">&#x27E8;NNT : &#x27E9;<\/a>. <a target=\"_blank\" href=\"https:\/\/inria.hal.science\/tel-04886659v1\">&#x27E8;tel-04886659&#x27E9;<\/a><\/li><\/ul><\/div><\/div><br><\/div>\n    <\/div>\n<\/div><div class=\"wphal-footer\"><p style=\"color:#B3B2B0\">Powered by HAL&nbsp;<a href=\"https:\/\/hal.science\/\" target=\"_blank\"><img decoding=\"async\" alt=\"logo\" src=\"https:\/\/project.inria.fr\/saif\/wp-content\/plugins\/hal\/img\/logo-hal.png\" style=\"width:90px\"><\/a><\/p><\/div><\/code><\/strong><\/p>","protected":false},"excerpt":{"rendered":"<p> <a class=\"continue-reading-link\" href=\"https:\/\/project.inria.fr\/saif\/publications\/\"><span>Continue reading<\/span><i class=\"crycon-right-dir\"><\/i><\/a> <\/p>\n","protected":false},"author":2389,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-141","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/project.inria.fr\/saif\/wp-json\/wp\/v2\/pages\/141","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/project.inria.fr\/saif\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/project.inria.fr\/saif\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/saif\/wp-json\/wp\/v2\/users\/2389"}],"replies":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/saif\/wp-json\/wp\/v2\/comments?post=141"}],"version-history":[{"count":8,"href":"https:\/\/project.inria.fr\/saif\/wp-json\/wp\/v2\/pages\/141\/revisions"}],"predecessor-version":[{"id":149,"href":"https:\/\/project.inria.fr\/saif\/wp-json\/wp\/v2\/pages\/141\/revisions\/149"}],"wp:attachment":[{"href":"https:\/\/project.inria.fr\/saif\/wp-json\/wp\/v2\/media?parent=141"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}