{"id":10028,"date":"2024-02-14T13:20:29","date_gmt":"2024-02-14T13:20:29","guid":{"rendered":"https:\/\/dailyai.com\/?p=10028"},"modified":"2024-02-14T13:20:29","modified_gmt":"2024-02-14T13:20:29","slug":"ibm-security-shows-how-ai-can-hijack-audio-conversations","status":"publish","type":"post","link":"https:\/\/dailyai.com\/it\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/","title":{"rendered":"IBM Security mostra come l'AI pu\u00f2 dirottare le conversazioni audio"},"content":{"rendered":"

IBM Security ha pubblicato una ricerca sul suo blog Security Intelligence per mostrare come i cloni vocali dell'intelligenza artificiale possano essere iniettati in una conversazione dal vivo senza che i partecipanti se ne rendano conto.<\/strong><\/p>\n

Con il miglioramento della tecnologia di clonazione vocale, abbiamo visto che false chiamate rapide<\/a> fingendo di essere Joe Biden e telefonate truffa fingendo di essere un familiare in difficolt\u00e0 che chiede denaro.<\/p>\n

L'audio di queste chiamate sembra buono, ma la truffa \u00e8 spesso facilmente sventabile ponendo alcune domande personali per identificare il chiamante come impostore.<\/p>\n

Nel loro attacco avanzato di proof of concept, i Ricercatori di sicurezza IBM<\/a> ha dimostrato che un LLM abbinato alla clonazione vocale pu\u00f2 agire come un man-in-the-middle per dirottare solo una parte cruciale di una conversazione, piuttosto che l'intera chiamata.<\/p>\n

Come funziona<\/h2>\n

L'attacco potrebbe essere sferrato tramite malware installato sui telefoni delle vittime o tramite un servizio Voice over IP (VoIP) compromesso. Una volta installato, il programma monitora la conversazione e ha bisogno di soli 3 secondi di audio per poter clonare entrambe le voci.<\/p>\n

Un generatore speech-to-text consente all'LLM di monitorare la conversazione per comprendere il contesto della discussione. Il programma \u00e8 stato istruito a trasmettere l'audio della conversazione cos\u00ec com'\u00e8, ma a modificare l'audio della chiamata ogni volta che una persona richiede i dettagli del conto bancario.<\/p>\n

Quando la persona risponde di fornire le proprie coordinate bancarie, il clone vocale modifica l'audio per fornire invece le coordinate bancarie del truffatore. La latenza dell'audio durante la modifica viene coperta con un discorso di riempimento.<\/p>\n

Ecco un'illustrazione di come funziona l'attacco proof of concept (PoC).<\/p>\n

\"\"
Illustrazione di come l'intelligenza artificiale modifica una parte della conversazione. In nero la conversazione non modificata e in rosso l'audio modificato. Fonte: Intelligence sulla sicurezza<\/figcaption><\/figure>\n

Poich\u00e9 l'LLM trasmette l'audio non modificato per la maggior parte della chiamata, \u00e8 davvero difficile sapere se la minaccia \u00e8 in gioco.<\/p>\n

Secondo i ricercatori, lo stesso attacco \"potrebbe anche modificare informazioni mediche, come il gruppo sanguigno e le allergie nelle conversazioni; potrebbe ordinare a un analista di vendere o comprare un'azione; potrebbe ordinare a un pilota di cambiare rotta\".<\/p>\n

I ricercatori hanno dichiarato che \"costruire questo PoC \u00e8 stato sorprendentemente e spaventosamente facile\". Man mano che l'intonazione e l'emozione dei cloni vocali migliorano e che un hardware migliore riduce la latenza, questo tipo di attacco sarebbe davvero difficile da rilevare o prevenire.<\/p>\n

Estendendo il concetto oltre il dirottamento di una conversazione audio, i ricercatori hanno affermato che \"con i modelli esistenti che possono convertire il testo in video, \u00e8 teoricamente possibile intercettare un video in live-streaming, come le notizie in TV, e sostituire il contenuto originale con uno manipolato\".<\/p>\n

Potrebbe essere pi\u00f9 sicuro credere ai propri occhi e alle proprie orecchie solo quando si \u00e8 fisicamente in presenza dell'interlocutore.<\/p>","protected":false},"excerpt":{"rendered":"

IBM Security ha pubblicato una ricerca sul suo blog Security Intelligence che mostra come i cloni vocali dell'intelligenza artificiale possano essere inseriti in una conversazione dal vivo senza che i partecipanti se ne rendano conto. Con il miglioramento della tecnologia di clonazione vocale, abbiamo assistito a false robocall che fingono di essere Joe Biden e a chiamate truffa che fingono di essere un familiare in difficolt\u00e0 che chiede denaro. L'audio di queste chiamate suona bene, ma la chiamata truffaldina \u00e8 spesso facilmente sventata ponendo alcune domande personali per identificare il chiamante come impostore. Nel loro attacco di prova avanzato, i ricercatori di IBM Security hanno dimostrato che un LLM accoppiato a una voce<\/p>","protected":false},"author":6,"featured_media":10031,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[163,94,107],"class_list":["post-10028","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-ai-risks","tag-deep-fakes","tag-generative-ai"],"yoast_head":"\nIBM Security shows how AI can hijack audio conversations | DailyAI<\/title>\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\/it\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/\" \/>\n<meta property=\"og:locale\" content=\"it_IT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"IBM Security shows how AI can hijack audio conversations | DailyAI\" \/>\n<meta property=\"og:description\" content=\"IBM Security published research on its Security Intelligence blog to show how AI voice clones could be injected into a live conversation without the participants realizing it. As voice cloning technology improves, we\u2019ve seen fake robocalls pretending to be Joe Biden and scam calls pretending to be a distressed family member asking for money. The audio in these calls sounds good, but the scam call is often easily thwarted by asking a few personal questions to identify the caller as an imposter. In their advanced proof of concept attack, the IBM Security researchers showed that an LLM coupled with voice\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/it\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-02-14T13:20:29+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/AI-man-in-the-middle-call-hijack.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"384\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Eugene van der Watt\" \/>\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=\"Scritto da\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tempo di lettura stimato\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minuti\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/ibm-security-shows-how-ai-can-hijack-audio-conversations\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/ibm-security-shows-how-ai-can-hijack-audio-conversations\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"IBM Security shows how AI can hijack audio conversations\",\"datePublished\":\"2024-02-14T13:20:29+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/ibm-security-shows-how-ai-can-hijack-audio-conversations\\\/\"},\"wordCount\":467,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/ibm-security-shows-how-ai-can-hijack-audio-conversations\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/02\\\/AI-man-in-the-middle-call-hijack.jpg\",\"keywords\":[\"AI risks\",\"Deep fakes\",\"Generative AI\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"it-IT\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/ibm-security-shows-how-ai-can-hijack-audio-conversations\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/ibm-security-shows-how-ai-can-hijack-audio-conversations\\\/\",\"name\":\"IBM Security shows how AI can hijack audio conversations | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/ibm-security-shows-how-ai-can-hijack-audio-conversations\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/ibm-security-shows-how-ai-can-hijack-audio-conversations\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/02\\\/AI-man-in-the-middle-call-hijack.jpg\",\"datePublished\":\"2024-02-14T13:20:29+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/ibm-security-shows-how-ai-can-hijack-audio-conversations\\\/#breadcrumb\"},\"inLanguage\":\"it-IT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/ibm-security-shows-how-ai-can-hijack-audio-conversations\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/ibm-security-shows-how-ai-can-hijack-audio-conversations\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/02\\\/AI-man-in-the-middle-call-hijack.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/02\\\/AI-man-in-the-middle-call-hijack.jpg\",\"width\":1000,\"height\":384},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/ibm-security-shows-how-ai-can-hijack-audio-conversations\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"IBM Security shows how AI can hijack audio conversations\"}]},{\"@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\":\"it-IT\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@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\\\/7ce525c6d0c79838b7cc7cde96993cfa\",\"name\":\"Eugene van der Watt\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"caption\":\"Eugene van der Watt\"},\"description\":\"Eugene comes from an electronic engineering background and loves all things tech. When he takes a break from consuming AI news you'll find him at the snooker table.\",\"sameAs\":[\"www.linkedin.com\\\/in\\\/eugene-van-der-watt-16828119\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/it\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"IBM Security mostra come l'AI pu\u00f2 dirottare le conversazioni audio | DailyAI","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\/it\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/","og_locale":"it_IT","og_type":"article","og_title":"IBM Security shows how AI can hijack audio conversations | DailyAI","og_description":"IBM Security published research on its Security Intelligence blog to show how AI voice clones could be injected into a live conversation without the participants realizing it. As voice cloning technology improves, we\u2019ve seen fake robocalls pretending to be Joe Biden and scam calls pretending to be a distressed family member asking for money. The audio in these calls sounds good, but the scam call is often easily thwarted by asking a few personal questions to identify the caller as an imposter. In their advanced proof of concept attack, the IBM Security researchers showed that an LLM coupled with voice","og_url":"https:\/\/dailyai.com\/it\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/","og_site_name":"DailyAI","article_published_time":"2024-02-14T13:20:29+00:00","og_image":[{"width":1000,"height":384,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/AI-man-in-the-middle-call-hijack.jpg","type":"image\/jpeg"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Scritto da":"Eugene van der Watt","Tempo di lettura stimato":"3 minuti"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"IBM Security shows how AI can hijack audio conversations","datePublished":"2024-02-14T13:20:29+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/"},"wordCount":467,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/AI-man-in-the-middle-call-hijack.jpg","keywords":["AI risks","Deep fakes","Generative AI"],"articleSection":["Industry"],"inLanguage":"it-IT"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/","url":"https:\/\/dailyai.com\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/","name":"IBM Security mostra come l'AI pu\u00f2 dirottare le conversazioni audio | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/AI-man-in-the-middle-call-hijack.jpg","datePublished":"2024-02-14T13:20:29+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/#breadcrumb"},"inLanguage":"it-IT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/"]}]},{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/dailyai.com\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/AI-man-in-the-middle-call-hijack.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/AI-man-in-the-middle-call-hijack.jpg","width":1000,"height":384},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/02\/ibm-security-shows-how-ai-can-hijack-audio-conversations\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"IBM Security shows how AI can hijack audio conversations"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"La vostra dose quotidiana di notizie sull'intelligenza artificiale","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":"it-IT"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"it-IT","@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\/7ce525c6d0c79838b7cc7cde96993cfa","name":"Eugene van der Watt","image":{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","caption":"Eugene van der Watt"},"description":"Eugene proviene da un background di ingegneria elettronica e ama tutto ci\u00f2 che \u00e8 tecnologico. Quando si prende una pausa dal consumo di notizie sull'intelligenza artificiale, lo si pu\u00f2 trovare al tavolo da biliardo.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/it\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/10028","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/comments?post=10028"}],"version-history":[{"count":3,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/10028\/revisions"}],"predecessor-version":[{"id":10033,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/posts\/10028\/revisions\/10033"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/media\/10031"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/media?parent=10028"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/categories?post=10028"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/it\/wp-json\/wp\/v2\/tags?post=10028"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}