{"id":837,"date":"2026-04-11T23:02:48","date_gmt":"2026-04-11T23:02:48","guid":{"rendered":"https:\/\/caisi.local\/research_project\/ethique-transparence-algorithmes\/"},"modified":"2026-04-20T23:41:38","modified_gmt":"2026-04-20T23:41:38","slug":"ethique-transparence-algorithmes","status":"publish","type":"research_project","link":"https:\/\/aisafety.ca\/fr\/research_project\/ethique-transparence-algorithmes\/","title":{"rendered":"La robustesse antagoniste dans les graphes de connaissances"},"content":{"rendered":"<p>L\u2019introduction de renseignements faux ou trompeurs dans les graphes de connaissances \u2013 les mod\u00e8les qui alimentent les agents de recherche et les agents conversationnels \u2013 a de graves cons\u00e9quences pour la s\u00e9curit\u00e9 de l\u2019IA, car elle permet \u00e0 la m\u00e9sinformation de s\u2019int\u00e9grer dans les mod\u00e8les et de se propager largement. Ebrahim Bagheri, professeur \u00e0 l\u2019Universit\u00e9 de Toronto, Jian Tang, titulaire de chaire en IA Canada-CIFAR, et Benjamin Fung, professeur \u00e0 l\u2019Universit\u00e9 McGill, concevront des d\u00e9fenses fond\u00e9es sur l\u2019apprentissage automatique afin de d\u00e9tecter et d\u2019att\u00e9nuer les modifications antagonistes dans les graphes de connaissances. En mettant au point des m\u00e9thodologies \u00e9volutives d\u2019entra\u00eenement antagoniste et d\u2019\u00e9valuation de la robustesse, leurs travaux de recherche permettront le d\u00e9ploiement pratique de graphes de connaissances plus s\u00fbrs dans le monde r\u00e9el.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u00c9laborer des strat\u00e9gies de d\u00e9fense en apprentissage automatique afin de d\u00e9tecter et de contrer les modifications antagonistes au sein des graphes de connaissances.<\/p>\n","protected":false},"featured_media":646,"template":"","ai-safety-technique":[63,60,66],"application-area":[69],"project-type":[85],"research-theme":[92,89],"class_list":["post-837","research_project","type-research_project","status-publish","has-post-thumbnail","hentry","ai-safety-technique-evaluation-et-analyse-comparative","ai-safety-technique-robustesse-antagoniste-et-methode-de-lequipe-rouge","ai-safety-technique-securite-integree-des-la-conception","application-area-ia-agentique-et-systemes-autonomes","project-type-projet-catalyseur","research-theme-ia-fiable-et-interpretable","research-theme-mesinformation-et-integrite-de-linformation"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.7 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>La robustesse antagoniste dans les graphes de connaissances<\/title>\n<meta name=\"description\" content=\"\u00c9laborer des strat\u00e9gies de d\u00e9fense en apprentissage automatique afin de d\u00e9tecter et de contrer les modifications antagonistes au sein des graphes de connaissances.\" \/>\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\/ethique-transparence-algorithmes\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"La robustesse antagoniste dans les graphes de connaissances\" \/>\n<meta property=\"og:description\" content=\"\u00c9laborer des strat\u00e9gies de d\u00e9fense en apprentissage automatique afin de d\u00e9tecter et de contrer les modifications antagonistes au sein des graphes de connaissances.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/aisafety.ca\/fr\/research_project\/ethique-transparence-algorithmes\/\" \/>\n<meta property=\"og:site_name\" content=\"CAISI\" \/>\n<meta property=\"article:modified_time\" content=\"2026-04-20T23:41:38+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-catalyst-colour-2.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=\"La robustesse antagoniste dans les graphes de connaissances\" \/>\n<meta name=\"twitter:description\" content=\"\u00c9laborer des strat\u00e9gies de d\u00e9fense en apprentissage automatique afin de d\u00e9tecter et de contrer les modifications antagonistes au sein des graphes de connaissances.\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-catalyst-colour-2.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\\\/ethique-transparence-algorithmes\\\/\",\"url\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/ethique-transparence-algorithmes\\\/\",\"name\":\"La robustesse antagoniste dans les graphes de connaissances\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/ethique-transparence-algorithmes\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/ethique-transparence-algorithmes\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/aisafety.ca\\\/wp-content\\\/uploads\\\/2026\\\/04\\\/projects-catalyst-colour-2.jpg\",\"datePublished\":\"2026-04-11T23:02:48+00:00\",\"dateModified\":\"2026-04-20T23:41:38+00:00\",\"description\":\"\u00c9laborer des strat\u00e9gies de d\u00e9fense en apprentissage automatique afin de d\u00e9tecter et de contrer les modifications antagonistes au sein des graphes de connaissances.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/ethique-transparence-algorithmes\\\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/ethique-transparence-algorithmes\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/ethique-transparence-algorithmes\\\/#primaryimage\",\"url\":\"https:\\\/\\\/aisafety.ca\\\/wp-content\\\/uploads\\\/2026\\\/04\\\/projects-catalyst-colour-2.jpg\",\"contentUrl\":\"https:\\\/\\\/aisafety.ca\\\/wp-content\\\/uploads\\\/2026\\\/04\\\/projects-catalyst-colour-2.jpg\",\"width\":1920,\"height\":1080,\"caption\":\"Abstract background with geometric shapes\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/research_project\\\/ethique-transparence-algorithmes\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/aisafety.ca\\\/fr\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"La robustesse antagoniste dans les graphes de connaissances\"}]},{\"@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":"La robustesse antagoniste dans les graphes de connaissances","description":"\u00c9laborer des strat\u00e9gies de d\u00e9fense en apprentissage automatique afin de d\u00e9tecter et de contrer les modifications antagonistes au sein des graphes de connaissances.","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\/ethique-transparence-algorithmes\/","og_locale":"fr_FR","og_type":"article","og_title":"La robustesse antagoniste dans les graphes de connaissances","og_description":"\u00c9laborer des strat\u00e9gies de d\u00e9fense en apprentissage automatique afin de d\u00e9tecter et de contrer les modifications antagonistes au sein des graphes de connaissances.","og_url":"https:\/\/aisafety.ca\/fr\/research_project\/ethique-transparence-algorithmes\/","og_site_name":"CAISI","article_modified_time":"2026-04-20T23:41:38+00:00","og_image":[{"width":1920,"height":1080,"url":"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-catalyst-colour-2.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_title":"La robustesse antagoniste dans les graphes de connaissances","twitter_description":"\u00c9laborer des strat\u00e9gies de d\u00e9fense en apprentissage automatique afin de d\u00e9tecter et de contrer les modifications antagonistes au sein des graphes de connaissances.","twitter_image":"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-catalyst-colour-2.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\/ethique-transparence-algorithmes\/","url":"https:\/\/aisafety.ca\/fr\/research_project\/ethique-transparence-algorithmes\/","name":"La robustesse antagoniste dans les graphes de connaissances","isPartOf":{"@id":"https:\/\/aisafety.ca\/fr\/#website"},"primaryImageOfPage":{"@id":"https:\/\/aisafety.ca\/fr\/research_project\/ethique-transparence-algorithmes\/#primaryimage"},"image":{"@id":"https:\/\/aisafety.ca\/fr\/research_project\/ethique-transparence-algorithmes\/#primaryimage"},"thumbnailUrl":"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-catalyst-colour-2.jpg","datePublished":"2026-04-11T23:02:48+00:00","dateModified":"2026-04-20T23:41:38+00:00","description":"\u00c9laborer des strat\u00e9gies de d\u00e9fense en apprentissage automatique afin de d\u00e9tecter et de contrer les modifications antagonistes au sein des graphes de connaissances.","breadcrumb":{"@id":"https:\/\/aisafety.ca\/fr\/research_project\/ethique-transparence-algorithmes\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/aisafety.ca\/fr\/research_project\/ethique-transparence-algorithmes\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/aisafety.ca\/fr\/research_project\/ethique-transparence-algorithmes\/#primaryimage","url":"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-catalyst-colour-2.jpg","contentUrl":"https:\/\/aisafety.ca\/wp-content\/uploads\/2026\/04\/projects-catalyst-colour-2.jpg","width":1920,"height":1080,"caption":"Abstract background with geometric shapes"},{"@type":"BreadcrumbList","@id":"https:\/\/aisafety.ca\/fr\/research_project\/ethique-transparence-algorithmes\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/aisafety.ca\/fr\/"},{"@type":"ListItem","position":2,"name":"La robustesse antagoniste dans les graphes de connaissances"}]},{"@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\/837","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\/646"}],"wp:attachment":[{"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/media?parent=837"}],"wp:term":[{"taxonomy":"ai-safety-technique","embeddable":true,"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/ai-safety-technique?post=837"},{"taxonomy":"application-area","embeddable":true,"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/application-area?post=837"},{"taxonomy":"project-type","embeddable":true,"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/project-type?post=837"},{"taxonomy":"research-theme","embeddable":true,"href":"https:\/\/aisafety.ca\/fr\/wp-json\/wp\/v2\/research-theme?post=837"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}