{"id":832,"date":"2026-04-11T23:02:48","date_gmt":"2026-04-11T23:02:48","guid":{"rendered":"https:\/\/caisi.local\/research_project\/securite-ia-theorie-des-jeux\/"},"modified":"2026-04-20T23:43:24","modified_gmt":"2026-04-20T23:43:24","slug":"securite-ia-theorie-des-jeux","status":"publish","type":"research_project","link":"https:\/\/aisafety.ca\/fr\/research_project\/securite-ia-theorie-des-jeux\/","title":{"rendered":"Assurer la s\u00e9curit\u00e9 des syst\u00e8mes d\u2019IA avanc\u00e9s par le recours \u00e0 la th\u00e9orie des jeux"},"content":{"rendered":"<p>\u00c0 l\u2019heure o\u00f9 les syst\u00e8mes d\u2019information deviennent de plus en plus autonomes et centr\u00e9s sur l\u2019IA, les cadres de s\u00e9curit\u00e9 traditionnels ne suffisent plus \u00e0 rem\u00e9dier aux enjeux de s\u00e9curit\u00e9, de contr\u00f4le et de protection de la confidentialit\u00e9, en particulier dans les situations o\u00f9 plusieurs agents d\u2019IA interagissent sans intervention humaine. Zhijing Jin, titulaire d\u2019une chaire en IA Canada-CIFAR, propose de recourir \u00e0 la th\u00e9orie des jeux, un cadre th\u00e9orique \u00e9prouv\u00e9, afin de fournir des garanties d\u00e9montrables visant \u00e0 limiter les comportements non conformes et \u00e0 offrir des outils concrets aux responsables politiques et aux \u00e9quipes de d\u00e9veloppement pour leur permettre de garder le contr\u00f4le sur les interactions multiagents.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Appliquer la th\u00e9orie des jeux pour offrir des garanties d\u00e9montrables contre les comportements non conformes et assurer un encadrement des interactions multiagents.<\/p>\n","protected":false},"featured_media":648,"template":"","ai-safety-technique":[61,66],"application-area":[80,69],"project-type":[84],"research-theme":[92],"class_list":["post-832","research_project","type-research_project","status-publish","has-post-thumbnail","hentry","ai-safety-technique-commandabilite-et-alignement","ai-safety-technique-securite-integree-des-la-conception","application-area-confidentialite-et-securite","application-area-ia-agentique-et-systemes-autonomes","project-type-projet-sur-lalignement-de-lia","research-theme-ia-fiable-et-interpretable"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.8 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Assurer la s\u00e9curit\u00e9 des syst\u00e8mes d\u2019IA avanc\u00e9s par le recours \u00e0 la th\u00e9orie des jeux<\/title>\n<meta name=\"description\" content=\"Appliquer la th\u00e9orie des jeux pour offrir des garanties d\u00e9montrables contre les comportements non conformes et assurer un encadrement des interactions multiagents.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/aisafety.ca\/fr\/research_project\/securite-ia-theorie-des-jeux\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Assurer la s\u00e9curit\u00e9 des syst\u00e8mes d\u2019IA avanc\u00e9s par le recours \u00e0 la th\u00e9orie des jeux\" \/>\n<meta property=\"og:description\" content=\"Appliquer la th\u00e9orie des jeux pour offrir des garanties d\u00e9montrables contre les comportements non conformes et assurer un encadrement des interactions multiagents.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/aisafety.ca\/fr\/research_project\/securite-ia-theorie-des-jeux\/\" \/>\n<meta property=\"og:site_name\" content=\"CAISI\" \/>\n<meta property=\"article:modified_time\" content=\"2026-04-20T23:43:24+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-ai-alignment-colour-1.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1920\" \/>\n\t<meta property=\"og:image:height\" content=\"1080\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:title\" content=\"Assurer la s\u00e9curit\u00e9 des syst\u00e8mes d\u2019IA avanc\u00e9s par le recours \u00e0 la th\u00e9orie des jeux\" \/>\n<meta name=\"twitter:description\" content=\"Appliquer la th\u00e9orie des jeux pour offrir des garanties d\u00e9montrables contre les comportements non conformes et assurer un encadrement des interactions multiagents.\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-ai-alignment-colour-1.jpg\" \/>\n<meta name=\"twitter:label1\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data1\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/securite-ia-theorie-des-jeux\\\/\",\"url\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/securite-ia-theorie-des-jeux\\\/\",\"name\":\"Assurer la s\u00e9curit\u00e9 des syst\u00e8mes d\u2019IA avanc\u00e9s par le recours \u00e0 la th\u00e9orie des jeux\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/securite-ia-theorie-des-jeux\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/securite-ia-theorie-des-jeux\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/aisafety.ca\\\/wp-content\\\/uploads\\\/2026\\\/04\\\/projects-ai-alignment-colour-1.jpg\",\"datePublished\":\"2026-04-11T23:02:48+00:00\",\"dateModified\":\"2026-04-20T23:43:24+00:00\",\"description\":\"Appliquer la th\u00e9orie des jeux pour offrir des garanties d\u00e9montrables contre les comportements non conformes et assurer un encadrement des interactions multiagents.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/securite-ia-theorie-des-jeux\\\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/securite-ia-theorie-des-jeux\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/securite-ia-theorie-des-jeux\\\/#primaryimage\",\"url\":\"https:\\\/\\\/aisafety.ca\\\/wp-content\\\/uploads\\\/2026\\\/04\\\/projects-ai-alignment-colour-1.jpg\",\"contentUrl\":\"https:\\\/\\\/aisafety.ca\\\/wp-content\\\/uploads\\\/2026\\\/04\\\/projects-ai-alignment-colour-1.jpg\",\"width\":1920,\"height\":1080,\"caption\":\"Abstract background with flowing shapes\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/securite-ia-theorie-des-jeux\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Assurer la s\u00e9curit\u00e9 des syst\u00e8mes d\u2019IA avanc\u00e9s par le recours \u00e0 la th\u00e9orie des jeux\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/#website\",\"url\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/\",\"name\":\"CAISI\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Assurer la s\u00e9curit\u00e9 des syst\u00e8mes d\u2019IA avanc\u00e9s par le recours \u00e0 la th\u00e9orie des jeux","description":"Appliquer la th\u00e9orie des jeux pour offrir des garanties d\u00e9montrables contre les comportements non conformes et assurer un encadrement des interactions multiagents.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/aisafety.ca\/fr\/research_project\/securite-ia-theorie-des-jeux\/","og_locale":"fr_FR","og_type":"article","og_title":"Assurer la s\u00e9curit\u00e9 des syst\u00e8mes d\u2019IA avanc\u00e9s par le recours \u00e0 la th\u00e9orie des jeux","og_description":"Appliquer la th\u00e9orie des jeux pour offrir des garanties d\u00e9montrables contre les comportements non conformes et assurer un encadrement des interactions multiagents.","og_url":"https:\/\/aisafety.ca\/fr\/research_project\/securite-ia-theorie-des-jeux\/","og_site_name":"CAISI","article_modified_time":"2026-04-20T23:43:24+00:00","og_image":[{"width":1920,"height":1080,"url":"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-ai-alignment-colour-1.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_title":"Assurer la s\u00e9curit\u00e9 des syst\u00e8mes d\u2019IA avanc\u00e9s par le recours \u00e0 la th\u00e9orie des jeux","twitter_description":"Appliquer la th\u00e9orie des jeux pour offrir des garanties d\u00e9montrables contre les comportements non conformes et assurer un encadrement des interactions multiagents.","twitter_image":"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-ai-alignment-colour-1.jpg","twitter_misc":{"Dur\u00e9e de lecture estim\u00e9e":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/aisafety.ca\/fr\/research_project\/securite-ia-theorie-des-jeux\/","url":"https:\/\/aisafety.ca\/fr\/research_project\/securite-ia-theorie-des-jeux\/","name":"Assurer la s\u00e9curit\u00e9 des syst\u00e8mes d\u2019IA avanc\u00e9s par le recours \u00e0 la th\u00e9orie des jeux","isPartOf":{"@id":"https:\/\/aisafety.ca\/fr\/#website"},"primaryImageOfPage":{"@id":"https:\/\/aisafety.ca\/fr\/research_project\/securite-ia-theorie-des-jeux\/#primaryimage"},"image":{"@id":"https:\/\/aisafety.ca\/fr\/research_project\/securite-ia-theorie-des-jeux\/#primaryimage"},"thumbnailUrl":"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-ai-alignment-colour-1.jpg","datePublished":"2026-04-11T23:02:48+00:00","dateModified":"2026-04-20T23:43:24+00:00","description":"Appliquer la th\u00e9orie des jeux pour offrir des garanties d\u00e9montrables contre les comportements non conformes et assurer un encadrement des interactions multiagents.","breadcrumb":{"@id":"https:\/\/aisafety.ca\/fr\/research_project\/securite-ia-theorie-des-jeux\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/aisafety.ca\/fr\/research_project\/securite-ia-theorie-des-jeux\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/aisafety.ca\/fr\/research_project\/securite-ia-theorie-des-jeux\/#primaryimage","url":"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-ai-alignment-colour-1.jpg","contentUrl":"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-ai-alignment-colour-1.jpg","width":1920,"height":1080,"caption":"Abstract background with flowing shapes"},{"@type":"BreadcrumbList","@id":"https:\/\/aisafety.ca\/fr\/research_project\/securite-ia-theorie-des-jeux\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/aisafety.ca\/fr\/"},{"@type":"ListItem","position":2,"name":"Assurer la s\u00e9curit\u00e9 des syst\u00e8mes d\u2019IA avanc\u00e9s par le recours \u00e0 la th\u00e9orie des jeux"}]},{"@type":"WebSite","@id":"https:\/\/aisafety.ca\/fr\/#website","url":"https:\/\/aisafety.ca\/fr\/","name":"CAISI","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/aisafety.ca\/fr\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"}]}},"_links":{"self":[{"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/research_project\/832","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/research_project"}],"about":[{"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/types\/research_project"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/media\/648"}],"wp:attachment":[{"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/media?parent=832"}],"wp:term":[{"taxonomy":"ai-safety-technique","embeddable":true,"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/ai-safety-technique?post=832"},{"taxonomy":"application-area","embeddable":true,"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/application-area?post=832"},{"taxonomy":"project-type","embeddable":true,"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/project-type?post=832"},{"taxonomy":"research-theme","embeddable":true,"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/research-theme?post=832"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}