{"id":8944,"date":"2024-01-06T20:37:14","date_gmt":"2024-01-06T20:37:14","guid":{"rendered":"https:\/\/dailyai.com\/?p=8944"},"modified":"2024-01-06T23:30:16","modified_gmt":"2024-01-06T23:30:16","slug":"the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks","status":"publish","type":"post","link":"https:\/\/dailyai.com\/fr\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/","title":{"rendered":"Le NIST publie un document sur les quatre types d'attaques possibles de l'IA g\u00e9n\u00e9rative"},"content":{"rendered":"

L'Institut national am\u00e9ricain des normes et de la technologie (NIST) a exprim\u00e9 des inqui\u00e9tudes quant \u00e0 la s\u00e9curit\u00e9 des syst\u00e8mes d'IA pr\u00e9dictive et g\u00e9n\u00e9rative.<\/b><\/p>\n

Selon Apostol Vassilev, informaticien au NIST, malgr\u00e9 les progr\u00e8s r\u00e9alis\u00e9s en mati\u00e8re de s\u00e9curit\u00e9, ces technologies restent vuln\u00e9rables \u00e0 diverses attaques.<\/span><\/p>\n

Dans un document de travail<\/a> titr\u00e9 \"<\/span>Apprentissage automatique adversarial : Une taxonomie et une terminologie des attaques et des att\u00e9nuations<\/span>Vassilev et ses coll\u00e8gues de la Northeastern University et de Robust Intelligence classent les risques de s\u00e9curit\u00e9 pos\u00e9s par les syst\u00e8mes d'IA.\u00a0<\/span><\/p>\n

M. Vassilev a d\u00e9clar\u00e9 : \"Malgr\u00e9 les progr\u00e8s consid\u00e9rables r\u00e9alis\u00e9s par l'IA et l'apprentissage automatique, ces technologies sont vuln\u00e9rables aux attaques qui peuvent provoquer des \u00e9checs spectaculaires aux cons\u00e9quences d\u00e9sastreuses.\"\u00a0<\/span><\/p>\n

Il a \u00e9galement mis en garde contre les entreprises qui pr\u00e9tendent offrir une \"IA enti\u00e8rement s\u00e9curis\u00e9e\".<\/span><\/p>\n

Cela fait partie de la <\/span>Initiative du NIST pour une IA digne de confiance et responsable<\/span><\/a>Il s'aligne sur les objectifs du gouvernement am\u00e9ricain en mati\u00e8re de s\u00e9curit\u00e9 de l'IA. Il examine les techniques adverses d'apprentissage automatique, en se concentrant sur quatre probl\u00e8mes de s\u00e9curit\u00e9 principaux : l'\u00e9vasion, l'empoisonnement, la protection de la vie priv\u00e9e et les attaques abusives.<\/span><\/p>\n

Les attaques d'\u00e9vasion se produisent apr\u00e8s le d\u00e9ploiement, en modifiant les donn\u00e9es d'entr\u00e9e pour confondre les syst\u00e8mes d'IA. Par exemple, modifier les panneaux d'arr\u00eat pour que les v\u00e9hicules autonomes les interpr\u00e8tent comme des panneaux de limitation de vitesse, ou cr\u00e9er des marquages de voies trompeurs pour \u00e9garer les v\u00e9hicules.<\/p>\n

Dans les attaques par empoisonnement, des donn\u00e9es corrompues sont introduites pendant la formation. Il peut s'agir de l'int\u00e9gration d'un langage inappropri\u00e9 fr\u00e9quent dans les ensembles de donn\u00e9es de formation, ce qui conduit un chatbot \u00e0 adopter ce langage dans les interactions avec les clients.<\/p>\n

Les attaques contre la vie priv\u00e9e visent \u00e0 extraire des informations sensibles sur l'IA ou ses donn\u00e9es de formation, souvent par des m\u00e9thodes de r\u00e9tro-ing\u00e9nierie. Il peut s'agir d'utiliser les r\u00e9ponses d'un chatbot pour discerner ses sources de formation et ses faiblesses.<\/p>\n

Les attaques par abus manipulent des sources l\u00e9gitimes, telles que des pages web, en fournissant aux syst\u00e8mes d'intelligence artificielle de fausses informations afin d'alt\u00e9rer leur fonctionnement. Cela diff\u00e8re des attaques par empoisonnement, qui corrompent le processus de formation lui-m\u00eame.<\/p>\n

Les attaques par \u00e9vasion consistent \u00e0 cr\u00e9er des exemples contradictoires pour tromper les syst\u00e8mes d'IA lors du d\u00e9ploiement, comme l'identification erron\u00e9e des panneaux d'arr\u00eat dans les v\u00e9hicules autonomes.\u00a0<\/span><\/p>\n

Alina Oprea de l'Universit\u00e9 de Northeastern, qui a particip\u00e9 \u00e0 l'\u00e9tude de la \u00e9tude<\/a>, <\/span>La plupart de ces attaques sont assez faciles \u00e0 mettre en place et n\u00e9cessitent une connaissance minimale du syst\u00e8me d'intelligence artificielle et des capacit\u00e9s adverses limit\u00e9es.<\/p>\n

Le NIST critiqu\u00e9 pour ses liens avec un groupe de r\u00e9flexion sur l'IA<\/h2>\n

S\u00e9par\u00e9ment, <\/span>des pr\u00e9occupations ont \u00e9t\u00e9 exprim\u00e9es<\/span><\/a> sur un projet de partenariat de recherche sur l'IA entre le NIST et la RAND Corp.<\/span><\/p>\n

La RAND, connue pour ses liens avec les milliardaires de la technologie et la <\/span>mouvement pour un altruisme efficace<\/span><\/a>Il a jou\u00e9 un r\u00f4le consultatif important dans l'\u00e9laboration de la politique de l'Union europ\u00e9enne en mati\u00e8re d'environnement.<\/span> D\u00e9cret sur la s\u00e9curit\u00e9 de l'IA<\/span><\/a>.\u00a0<\/span><\/p>\n

Les membres de la commission de la science, de l'espace et de la technologie de la Chambre des repr\u00e9sentants, dont Frank Lucas et Zoe Lofgren, ont critiqu\u00e9 le manque de transparence de ce partenariat.\u00a0<\/span><\/p>\n

Les pr\u00e9occupations de la commission sont doubles : Premi\u00e8rement, elle se demande pourquoi il n'y a pas eu de proc\u00e9dure concurrentielle pour s\u00e9lectionner la RAND pour cette recherche sur la s\u00e9curit\u00e9 de l'IA.\u00a0<\/span><\/p>\n

Habituellement, lorsque des agences gouvernementales comme le NIST accordent des subventions de recherche, elles donnent la possibilit\u00e9 \u00e0 diff\u00e9rentes organisations de poser leur candidature, ce qui garantit un processus de s\u00e9lection \u00e9quitable. Mais dans le cas pr\u00e9sent, il semble que la RAND ait \u00e9t\u00e9 choisie sans cette proc\u00e9dure.<\/span><\/p>\n

Deuxi\u00e8mement, l'accent mis par la RAND sur la recherche en mati\u00e8re d'IA suscite un certain malaise. La RAND a particip\u00e9 \u00e0 des \u00e9tudes sur l'IA et la bios\u00e9curit\u00e9 et a r\u00e9cemment re\u00e7u un financement important pour ces travaux de la part de sources \u00e9troitement li\u00e9es \u00e0 l'industrie technologique.\u00a0<\/span><\/p>","protected":false},"excerpt":{"rendered":"

Le National Institute of Standards and Technology (NIST) des \u00c9tats-Unis s'inqui\u00e8te de la s\u00e9curit\u00e9 des syst\u00e8mes d'IA pr\u00e9dictive et g\u00e9n\u00e9rative. Selon Apostol Vassilev, informaticien au NIST, malgr\u00e9 les progr\u00e8s r\u00e9alis\u00e9s en mati\u00e8re de s\u00e9curit\u00e9, ces technologies restent vuln\u00e9rables \u00e0 diverses attaques. Dans un article collectif intitul\u00e9 \"Adversarial Machine Learning : A Taxonomy and Terminology of Attacks and Mitigations\", M. Vassilev, ainsi que des coll\u00e8gues de la Northeastern University et de Robust Intelligence, classent les risques de s\u00e9curit\u00e9 pos\u00e9s par les syst\u00e8mes d'IA. M. Vassilev a d\u00e9clar\u00e9 : \"Malgr\u00e9 les progr\u00e8s consid\u00e9rables r\u00e9alis\u00e9s par l'IA et l'apprentissage automatique, ces technologies sont vuln\u00e9rables aux attaques qui peuvent provoquer des \u00e9checs spectaculaires<\/p>","protected":false},"author":2,"featured_media":8945,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[512],"class_list":["post-8944","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-nist"],"yoast_head":"\nThe NIST publishes paper on four possible types of generative AI attacks | DailyAI<\/title>\n<meta name=\"description\" content=\"The US National Institute of Standards and Technology (NIST) has released a new paper on the risks of generative AI.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/fr\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"The NIST publishes paper on four possible types of generative AI attacks | DailyAI\" \/>\n<meta property=\"og:description\" content=\"The US National Institute of Standards and Technology (NIST) has released a new paper on the risks of generative AI.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/fr\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-01-06T20:37:14+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-01-06T23:30:16+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/shutterstock_1905754738.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"667\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Sam Jeans\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"\u00c9crit par\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sam Jeans\" \/>\n\t<meta name=\"twitter:label2\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\\\/\"},\"author\":{\"name\":\"Sam Jeans\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\"},\"headline\":\"The NIST publishes paper on four possible types of generative AI attacks\",\"datePublished\":\"2024-01-06T20:37:14+00:00\",\"dateModified\":\"2024-01-06T23:30:16+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\\\/\"},\"wordCount\":513,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/shutterstock_1905754738.jpg\",\"keywords\":[\"NIST\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"fr-FR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\\\/\",\"name\":\"The NIST publishes paper on four possible types of generative AI attacks | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/shutterstock_1905754738.jpg\",\"datePublished\":\"2024-01-06T20:37:14+00:00\",\"dateModified\":\"2024-01-06T23:30:16+00:00\",\"description\":\"The US National Institute of Standards and Technology (NIST) has released a new paper on the risks of generative AI.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\\\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/shutterstock_1905754738.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/01\\\/shutterstock_1905754738.jpg\",\"width\":1000,\"height\":667,\"caption\":\"NIST\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/01\\\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"The NIST publishes paper on four possible types of generative AI attacks\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\",\"name\":\"Sam Jeans\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"caption\":\"Sam Jeans\"},\"description\":\"Sam is a science and technology writer who has worked in various AI startups. When he\u2019s not writing, he can be found reading medical journals or digging through boxes of vinyl records.\",\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/in\\\/sam-jeans-6746b9142\\\/\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/fr\\\/author\\\/samjeans\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Le NIST publie un document sur les quatre types d'attaques possibles de l'IA g\u00e9n\u00e9rative | DailyAI","description":"Le National Institute of Standards and Technology (NIST) des \u00c9tats-Unis a publi\u00e9 un nouveau document sur les risques de l'IA g\u00e9n\u00e9rative.","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:\/\/dailyai.com\/fr\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/","og_locale":"fr_FR","og_type":"article","og_title":"The NIST publishes paper on four possible types of generative AI attacks | DailyAI","og_description":"The US National Institute of Standards and Technology (NIST) has released a new paper on the risks of generative AI.","og_url":"https:\/\/dailyai.com\/fr\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/","og_site_name":"DailyAI","article_published_time":"2024-01-06T20:37:14+00:00","article_modified_time":"2024-01-06T23:30:16+00:00","og_image":[{"width":1000,"height":667,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/shutterstock_1905754738.jpg","type":"image\/jpeg"}],"author":"Sam Jeans","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"\u00c9crit par":"Sam Jeans","Dur\u00e9e de lecture estim\u00e9e":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/"},"author":{"name":"Sam Jeans","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9"},"headline":"The NIST publishes paper on four possible types of generative AI attacks","datePublished":"2024-01-06T20:37:14+00:00","dateModified":"2024-01-06T23:30:16+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/"},"wordCount":513,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/shutterstock_1905754738.jpg","keywords":["NIST"],"articleSection":["Industry"],"inLanguage":"fr-FR"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/","url":"https:\/\/dailyai.com\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/","name":"Le NIST publie un document sur les quatre types d'attaques possibles de l'IA g\u00e9n\u00e9rative | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/shutterstock_1905754738.jpg","datePublished":"2024-01-06T20:37:14+00:00","dateModified":"2024-01-06T23:30:16+00:00","description":"Le National Institute of Standards and Technology (NIST) des \u00c9tats-Unis a publi\u00e9 un nouveau document sur les risques de l'IA g\u00e9n\u00e9rative.","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/dailyai.com\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/shutterstock_1905754738.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/01\/shutterstock_1905754738.jpg","width":1000,"height":667,"caption":"NIST"},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/01\/the-nist-publishes-paper-on-four-possible-types-of-generative-ai-attacks\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"The NIST publishes paper on four possible types of generative AI attacks"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"Votre dose quotidienne de nouvelles sur l'IA","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9","name":"Sam Jeans","image":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","caption":"Sam Jeans"},"description":"Sam est un r\u00e9dacteur scientifique et technologique qui a travaill\u00e9 dans diverses start-ups sp\u00e9cialis\u00e9es dans l'IA. Lorsqu'il n'\u00e9crit pas, on peut le trouver en train de lire des revues m\u00e9dicales ou de fouiller dans des bo\u00eetes de disques vinyles.","sameAs":["https:\/\/www.linkedin.com\/in\/sam-jeans-6746b9142\/"],"url":"https:\/\/dailyai.com\/fr\/author\/samjeans\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/8944","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/comments?post=8944"}],"version-history":[{"count":6,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/8944\/revisions"}],"predecessor-version":[{"id":8954,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/8944\/revisions\/8954"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media\/8945"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media?parent=8944"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/categories?post=8944"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/tags?post=8944"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}