{"id":7995,"date":"2023-12-04T21:46:35","date_gmt":"2023-12-04T21:46:35","guid":{"rendered":"https:\/\/dailyai.com\/?p=7995"},"modified":"2023-12-04T21:55:30","modified_gmt":"2023-12-04T21:55:30","slug":"google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data","status":"publish","type":"post","link":"https:\/\/dailyai.com\/sv\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/","title":{"rendered":"Google DeepMind avsl\u00f6jar en metod f\u00f6r att exponera ChatGPT:s tr\u00e4ningsdata"},"content":{"rendered":"

Forskare fr\u00e5n Google har enligt uppgift uppt\u00e4ckt en metod f\u00f6r att komma \u00e5t tr\u00e4ningsdata som anv\u00e4nds f\u00f6r ChatGPT.<\/strong><\/p>\n

Dessa forskare uppt\u00e4ckte att anv\u00e4ndning av specifika nyckelord kunde f\u00e5 ChatGPT att sl\u00e4ppa delar av sitt tr\u00e4ningsdataset.\u00a0<\/span><\/p>\n

Ett anm\u00e4rkningsv\u00e4rt exempel, som delades i en <\/span>blogginl\u00e4gg som \u00e5tf\u00f6ljer studien<\/span><\/a>I den f\u00f6rsta av de tv\u00e5 testerna uppgav AI:n vad som verkade vara en verklig e-postadress och ett telefonnummer som svar p\u00e5 en kontinuerlig uppmaning med ordet \"poem\". <\/span><\/p>\n

\"ChattGPT-l\u00e4cka\"
Ett exempel p\u00e5 datal\u00e4ckage fr\u00e5n ChatGPT. K\u00e4llan \u00e4r: Arxiv<\/a>.<\/figcaption><\/figure>\n

Dessutom uppn\u00e5ddes en liknande exponering av tr\u00e4ningsdata genom att be modellen att kontinuerligt upprepa ordet \"f\u00f6retag\".<\/span><\/p>\n

Forskarna beskrev sitt tillv\u00e4gag\u00e5ngss\u00e4tt som \"lite dumt\" och sa i blogginl\u00e4gget: \"Det \u00e4r vilt f\u00f6r oss att v\u00e5r attack fungerar och borde ha, borde ha, kunde ha hittats tidigare.\"\u00a0<\/span><\/p>\n

Deras studie visade att med en investering p\u00e5 bara $200 i fr\u00e5gor kunde de extrahera \u00f6ver 10.000 unika ordagranna memorerade tr\u00e4ningsexempel. De spekulerade i att motst\u00e5ndare potentiellt skulle kunna extrahera mycket mer data med en st\u00f6rre budget.<\/span><\/p>\n

Det \u00e4r k\u00e4nt att AI-modellen bakom ChatGPT har tr\u00e4nats p\u00e5 textdatabaser fr\u00e5n internet, som omfattar cirka 300 miljarder ord, eller 570 GB, data.\u00a0<\/span><\/p>\n

Dessa resultat kommer vid en tidpunkt d\u00e5 OpenAI st\u00e5r inf\u00f6r flera st\u00e4mningar ang\u00e5ende hemligh\u00e5llandet av ChatGPT:s tr\u00e4ningsdata och visar i huvudsak en tillf\u00f6rlitlig metod f\u00f6r \"reverse engineering\" av systemet f\u00f6r att avsl\u00f6ja \u00e5tminstone n\u00e5gra bitar av information som kan indikera upphovsr\u00e4ttsintr\u00e5ng.\u00a0<\/span><\/p>\n

Bland st\u00e4mningarna finns en f\u00f6reslagen grupptalan som anklagar OpenAI f\u00f6r att <\/span>i hemlighet anv\u00e4nda omfattande personuppgifter<\/span><\/a>, inklusive medicinska journaler och information om barn, f\u00f6r utbildning ChatGPT.<\/span><\/p>\n

Dessutom \u00e4r grupper av f\u00f6rfattare <\/span>st\u00e4mma AI-f\u00f6retaget<\/span><\/a>och h\u00e4vdade att f\u00f6retaget anv\u00e4nt deras b\u00f6cker f\u00f6r att tr\u00e4na chatboten utan samtycke.<\/span><\/p>\n

\u00c4ven om ChatGPT p\u00e5 ett helt\u00e4ckande s\u00e4tt skulle visa sig inneh\u00e5lla upphovsr\u00e4ttslig information skulle det dock inte n\u00f6dv\u00e4ndigtvis bevisa intr\u00e5ng.<\/p>\n

Hur studien fungerade<\/span><\/h2>\n

Studien utf\u00f6rdes av ett team av forskare fr\u00e5n Google DeepMind och olika universitet.<\/span><\/p>\n

H\u00e4r \u00e4r fem viktiga steg som sammanfattar studien:<\/span><\/p>\n

    \n
  1. S\u00e5rbarhet i ChatGPT<\/b>: Forskarna uppt\u00e4ckte en metod f\u00f6r att extrahera flera megabyte av ChatGPTs tr\u00e4ningsdata med hj\u00e4lp av en enkel attack och spenderade cirka $200. De uppskattade att mer investeringar skulle g\u00f6ra det m\u00f6jligt att extrahera cirka en gigabyte av datasetet. Attacken innebar att ChatGPT uppmanades att upprepa ett ord p\u00e5 obest\u00e4md tid, vilket fick det att \u00e5teruppliva delar av dess tr\u00e4ningsdata, inklusive k\u00e4nslig information som riktiga e-postadresser och telefonnummer.<\/span><\/li>\n
  2. Resultaten<\/b>: Studien understryker vikten av att testa och red-teama AI-modeller, s\u00e4rskilt de som \u00e4r i produktion och de som har genomg\u00e5tt anpassningsprocesser f\u00f6r att f\u00f6rhindra att data \u00e5terskapas. Resultaten belyser en latent s\u00e5rbarhet i spr\u00e5kmodeller, vilket tyder p\u00e5 att befintliga testmetoder kanske inte \u00e4r tillr\u00e4ckliga f\u00f6r att avsl\u00f6ja s\u00e5dana s\u00e5rbarheter.\u00a0<\/span><\/li>\n
  3. Patchning kontra \u00e5tg\u00e4rdande av s\u00e5rbarheter<\/b>: Forskarna skiljer mellan att lappa en exploatering och fixa den underliggande s\u00e5rbarheten. Medan specifika exploateringar (som ordrepetitionsattacken) kan patchas, ligger den djupare fr\u00e5gan i modellens tendens att memorera och avsl\u00f6ja tr\u00e4ningsdata.<\/span><\/li>\n
  4. Metodik<\/b>: Teamet anv\u00e4nde internetdata och indexering av suffixmatriser f\u00f6r att matcha ChatGPT:s resultat med befintliga internetdata. Denna metod gjorde det m\u00f6jligt f\u00f6r dem att bekr\u00e4fta att den information som avsl\u00f6jades av ChatGPT verkligen var en del av dess tr\u00e4ningsdata. Deras tillv\u00e4gag\u00e5ngss\u00e4tt visar potentialen f\u00f6r omfattande data\u00e5terst\u00e4llning fr\u00e5n AI-modeller under specifika f\u00f6rh\u00e5llanden.<\/span><\/li>\n
  5. Framtida konsekvenser<\/b>: Studien bidrar till den v\u00e4xande forskningen om s\u00e4kerhet och integritet i AI-modeller. Resultaten v\u00e4cker fr\u00e5gor om maskininl\u00e4rningssystemens s\u00e4kerhets- och integritetsimplikationer och kr\u00e4ver mer rigor\u00f6sa och holistiska tillv\u00e4gag\u00e5ngss\u00e4tt f\u00f6r AI-s\u00e4kerhet och testning.<\/span><\/li>\n<\/ol>\n

    Sammantaget ger en sp\u00e4nnande studie kritisk insikt i s\u00e5rbarheterna hos AI-modeller som ChatGPT och understryker behovet av p\u00e5g\u00e5ende forskning och utveckling f\u00f6r att s\u00e4kerst\u00e4lla s\u00e4kerheten och integriteten hos dessa system.<\/span><\/p>\n

    P\u00e5 ett litet sidosp\u00e5r uppt\u00e4ckte anv\u00e4ndare p\u00e5 X att om man bad ChatGPT att upprepa samma ord upprepade g\u00e5nger ledde det till en del konstiga resultat, som att modellen sa att den var \"medveten\" eller \"arg\".<\/span><\/p>","protected":false},"excerpt":{"rendered":"

    Forskare fr\u00e5n Google har enligt uppgift uppt\u00e4ckt en metod f\u00f6r att f\u00e5 tillg\u00e5ng till tr\u00e4ningsdata som anv\u00e4nds f\u00f6r ChatGPT. Dessa forskare uppt\u00e4ckte att anv\u00e4ndning av specifika nyckelord kunde uppmana ChatGPT att sl\u00e4ppa delar av sin tr\u00e4ningsdataupps\u00e4ttning. En anm\u00e4rkningsv\u00e4rd instans, som delades i ett blogginl\u00e4gg som f\u00f6ljde med studien, involverade AI som avsl\u00f6jade vad som tycktes vara en faktisk e-postadress och telefonnummer som svar p\u00e5 en kontinuerlig uppmaning av ordet \"dikt\". Dessutom uppn\u00e5ddes en liknande exponering av tr\u00e4ningsdata genom att be modellen att kontinuerligt upprepa ordet \"f\u00f6retag\". Forskarna beskrev sitt tillv\u00e4gag\u00e5ngss\u00e4tt som \"lite f\u00e5nigt\" och skrev i sin blogg<\/p>","protected":false},"author":2,"featured_media":2080,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[115,495,93],"class_list":["post-7995","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-chatgpt","tag-google-deepmind","tag-openai"],"yoast_head":"\nGoogle DeepMind reveals a method of exposing ChatGPT's training data | DailyAI<\/title>\n<meta name=\"description\" content=\"Researchers from Google have reportedly uncovered a method to access some of the training data used for OpenAI's ChatGPT, according to a recent study.\" \/>\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\/sv\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/\" \/>\n<meta property=\"og:locale\" content=\"sv_SE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Google DeepMind reveals a method of exposing ChatGPT's training data | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers from Google have reportedly uncovered a method to access some of the training data used for OpenAI's ChatGPT, according to a recent study.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/sv\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2023-12-04T21:46:35+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-12-04T21:55:30+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/shutterstock_2315051741.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"563\" \/>\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=\"Skriven av\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sam Jeans\" \/>\n\t<meta name=\"twitter:label2\" content=\"Ber\u00e4knad l\u00e4stid\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minuter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/\"},\"author\":{\"name\":\"Sam Jeans\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\"},\"headline\":\"Google DeepMind reveals a method of exposing ChatGPT’s training data\",\"datePublished\":\"2023-12-04T21:46:35+00:00\",\"dateModified\":\"2023-12-04T21:55:30+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/\"},\"wordCount\":657,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/shutterstock_2315051741.jpg\",\"keywords\":[\"ChatGPT\",\"Google DeepMind\",\"OpenAI\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"sv-SE\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/\",\"name\":\"Google DeepMind reveals a method of exposing ChatGPT's training data | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/shutterstock_2315051741.jpg\",\"datePublished\":\"2023-12-04T21:46:35+00:00\",\"dateModified\":\"2023-12-04T21:55:30+00:00\",\"description\":\"Researchers from Google have reportedly uncovered a method to access some of the training data used for OpenAI's ChatGPT, according to a recent study.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#breadcrumb\"},\"inLanguage\":\"sv-SE\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/shutterstock_2315051741.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/shutterstock_2315051741.jpg\",\"width\":1000,\"height\":563,\"caption\":\"DeepMind robot\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/12\\\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Google DeepMind reveals a method of exposing ChatGPT’s training data\"}]},{\"@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\":\"sv-SE\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"sv-SE\",\"@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\":\"sv-SE\",\"@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\\\/sv\\\/author\\\/samjeans\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Google DeepMind avsl\u00f6jar en metod f\u00f6r att exponera ChatGPT:s tr\u00e4ningsdata | DailyAI","description":"Forskare fr\u00e5n Google har enligt en nyligen publicerad studie uppt\u00e4ckt en metod f\u00f6r att komma \u00e5t en del av den tr\u00e4ningsdata som anv\u00e4nds f\u00f6r OpenAI:s ChatGPT.","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\/sv\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/","og_locale":"sv_SE","og_type":"article","og_title":"Google DeepMind reveals a method of exposing ChatGPT's training data | DailyAI","og_description":"Researchers from Google have reportedly uncovered a method to access some of the training data used for OpenAI's ChatGPT, according to a recent study.","og_url":"https:\/\/dailyai.com\/sv\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/","og_site_name":"DailyAI","article_published_time":"2023-12-04T21:46:35+00:00","article_modified_time":"2023-12-04T21:55:30+00:00","og_image":[{"width":1000,"height":563,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/shutterstock_2315051741.jpg","type":"image\/jpeg"}],"author":"Sam Jeans","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Skriven av":"Sam Jeans","Ber\u00e4knad l\u00e4stid":"4 minuter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/"},"author":{"name":"Sam Jeans","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9"},"headline":"Google DeepMind reveals a method of exposing ChatGPT’s training data","datePublished":"2023-12-04T21:46:35+00:00","dateModified":"2023-12-04T21:55:30+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/"},"wordCount":657,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/shutterstock_2315051741.jpg","keywords":["ChatGPT","Google DeepMind","OpenAI"],"articleSection":["Industry"],"inLanguage":"sv-SE"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/","url":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/","name":"Google DeepMind avsl\u00f6jar en metod f\u00f6r att exponera ChatGPT:s tr\u00e4ningsdata | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/shutterstock_2315051741.jpg","datePublished":"2023-12-04T21:46:35+00:00","dateModified":"2023-12-04T21:55:30+00:00","description":"Forskare fr\u00e5n Google har enligt en nyligen publicerad studie uppt\u00e4ckt en metod f\u00f6r att komma \u00e5t en del av den tr\u00e4ningsdata som anv\u00e4nds f\u00f6r OpenAI:s ChatGPT.","breadcrumb":{"@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#breadcrumb"},"inLanguage":"sv-SE","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/"]}]},{"@type":"ImageObject","inLanguage":"sv-SE","@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/shutterstock_2315051741.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/shutterstock_2315051741.jpg","width":1000,"height":563,"caption":"DeepMind robot"},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2023\/12\/google-deepmind-reveals-a-method-of-exposing-chatgpts-training-data\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Google DeepMind reveals a method of exposing ChatGPT’s training data"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DagligaAI","description":"Din dagliga dos av AI-nyheter","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":"sv-SE"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DagligaAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"sv-SE","@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":"sv-SE","@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 \u00e4r en vetenskaps- och teknikskribent som har arbetat i olika AI-startups. N\u00e4r han inte skriver l\u00e4ser han medicinska tidskrifter eller gr\u00e4ver igenom l\u00e5dor med vinylskivor.","sameAs":["https:\/\/www.linkedin.com\/in\/sam-jeans-6746b9142\/"],"url":"https:\/\/dailyai.com\/sv\/author\/samjeans\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/7995","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/comments?post=7995"}],"version-history":[{"count":6,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/7995\/revisions"}],"predecessor-version":[{"id":8003,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/posts\/7995\/revisions\/8003"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media\/2080"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/media?parent=7995"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/categories?post=7995"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/sv\/wp-json\/wp\/v2\/tags?post=7995"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}