{"id":13680,"date":"2024-10-23T09:54:00","date_gmt":"2024-10-23T09:54:00","guid":{"rendered":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/"},"modified":"2024-10-23T09:54:00","modified_gmt":"2024-10-23T09:54:00","slug":"researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news","status":"publish","type":"post","link":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/","title":{"rendered":"Researchers Reveal &#8216;Deceptive Delight&#8217; Method to Jailbreak AI Models info@thehackernews.com (The Hacker News)"},"content":{"rendered":"<p>Cybersecurity researchers have shed light on a new adversarial technique that could be used to jailbreak large language models (LLMs) during the course of an interactive conversation by sneaking in an undesirable instruction between benign ones.<br \/>\nThe approach has been codenamed Deceptive Delight by Palo Alto Networks Unit 42, which described it as both simple and effective, achieving an average<a href=\"https:\/\/thehackernews.com\/2024\/10\/researchers-reveal-deceptive-delight.html\" target=\"_blank\" class=\"feedzy-rss-link-icon\" rel=\"noopener\">Read More<\/a>\u00a0<\/p>","protected":false},"excerpt":{"rendered":"<p>Cybersecurity researchers have shed light on a new adversarial technique that could be used to jailbreak large language models (LLMs) during the course of an interactive conversation by sneaking in an undesirable instruction between benign ones. The approach has been codenamed Deceptive Delight by Palo Alto Networks Unit 42, which described it as both simple [&hellip;]<\/p>\n","protected":false},"author":0,"featured_media":13681,"comment_status":"","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[1],"tags":[],"class_list":["post-13680","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 4.9.8 - aioseo.com -->\n\t<meta name=\"description\" content=\"Cybersecurity researchers have shed light on a new adversarial technique that could be used to jailbreak large language models (LLMs) during the course of an interactive conversation by sneaking in an undesirable instruction between benign ones. The approach has been codenamed Deceptive Delight by Palo Alto Networks Unit 42, which described it as both simple\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<link rel=\"canonical\" href=\"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 4.9.8\" \/>\n\t\t<meta property=\"og:locale\" content=\"en_US\" \/>\n\t\t<meta property=\"og:site_name\" content=\"Sekuritas IT \u203a Creative solutions to unique challenges.\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"Researchers Reveal \u2018Deceptive Delight\u2019 Method to Jailbreak AI Models info@thehackernews.com (The Hacker News) \u203a Sekuritas IT\" \/>\n\t\t<meta property=\"og:description\" content=\"Cybersecurity researchers have shed light on a new adversarial technique that could be used to jailbreak large language models (LLMs) during the course of an interactive conversation by sneaking in an undesirable instruction between benign ones. The approach has been codenamed Deceptive Delight by Palo Alto Networks Unit 42, which described it as both simple\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2024-10-23T09:54:00+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2024-10-23T09:54:00+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/profile.php?id=100086973577423\" \/>\n\t\t<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n\t\t<meta name=\"twitter:title\" content=\"Researchers Reveal \u2018Deceptive Delight\u2019 Method to Jailbreak AI Models info@thehackernews.com (The Hacker News) \u203a Sekuritas IT\" \/>\n\t\t<meta name=\"twitter:description\" content=\"Cybersecurity researchers have shed light on a new adversarial technique that could be used to jailbreak large language models (LLMs) during the course of an interactive conversation by sneaking in an undesirable instruction between benign ones. The approach has been codenamed Deceptive Delight by Palo Alto Networks Unit 42, which described it as both simple\" \/>\n\t\t<script type=\"application\/ld+json\" class=\"aioseo-schema\">\n\t\t\t{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"BlogPosting\",\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/2024\\\/10\\\/23\\\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\\\/#blogposting\",\"name\":\"Researchers Reveal \\u2018Deceptive Delight\\u2019 Method to Jailbreak AI Models info@thehackernews.com (The Hacker News) \\u203a Sekuritas IT\",\"headline\":\"Researchers Reveal &#8216;Deceptive Delight&#8217; Method to Jailbreak AI Models info@thehackernews.com (The Hacker News)\",\"author\":{\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/author\\\/#author\"},\"publisher\":{\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/#organization\"},\"image\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/sekuritasit.com\\\/wp-content\\\/uploads\\\/2024\\\/10\\\/ai-jailbreak-f8rEk8.png\",\"width\":728,\"height\":380},\"datePublished\":\"2024-10-23T09:54:00+00:00\",\"dateModified\":\"2024-10-23T09:54:00+00:00\",\"inLanguage\":\"en-US\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/2024\\\/10\\\/23\\\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\\\/#webpage\"},\"isPartOf\":{\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/2024\\\/10\\\/23\\\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\\\/#webpage\"},\"articleSection\":\"Uncategorized\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/2024\\\/10\\\/23\\\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\\\/#breadcrumblist\",\"itemListElement\":[{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/sekuritasit.com#listItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/sekuritasit.com\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/category\\\/uncategorized\\\/#listItem\",\"name\":\"Uncategorized\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/category\\\/uncategorized\\\/#listItem\",\"position\":2,\"name\":\"Uncategorized\",\"item\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/category\\\/uncategorized\\\/\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/2024\\\/10\\\/23\\\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\\\/#listItem\",\"name\":\"Researchers Reveal &#8216;Deceptive Delight&#8217; Method to Jailbreak AI Models info@thehackernews.com (The Hacker News)\"},\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/sekuritasit.com#listItem\",\"name\":\"Home\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/2024\\\/10\\\/23\\\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\\\/#listItem\",\"position\":3,\"name\":\"Researchers Reveal &#8216;Deceptive Delight&#8217; Method to Jailbreak AI Models info@thehackernews.com (The Hacker News)\",\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/category\\\/uncategorized\\\/#listItem\",\"name\":\"Uncategorized\"}}]},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/#organization\",\"name\":\"Sekuritas IT\",\"description\":\"Creative solutions to unique challenges.\",\"url\":\"https:\\\/\\\/sekuritasit.com\\\/\",\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/profile.php?id=100086973577423\"]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/2024\\\/10\\\/23\\\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\\\/#webpage\",\"url\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/2024\\\/10\\\/23\\\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\\\/\",\"name\":\"Researchers Reveal \\u2018Deceptive Delight\\u2019 Method to Jailbreak AI Models info@thehackernews.com (The Hacker News) \\u203a Sekuritas IT\",\"description\":\"Cybersecurity researchers have shed light on a new adversarial technique that could be used to jailbreak large language models (LLMs) during the course of an interactive conversation by sneaking in an undesirable instruction between benign ones. The approach has been codenamed Deceptive Delight by Palo Alto Networks Unit 42, which described it as both simple\",\"inLanguage\":\"en-US\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/#website\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/2024\\\/10\\\/23\\\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\\\/#breadcrumblist\"},\"author\":{\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/author\\\/#author\"},\"creator\":{\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/author\\\/#author\"},\"image\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/sekuritasit.com\\\/wp-content\\\/uploads\\\/2024\\\/10\\\/ai-jailbreak-f8rEk8.png\",\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/2024\\\/10\\\/23\\\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\\\/#mainImage\",\"width\":728,\"height\":380},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/index.php\\\/2024\\\/10\\\/23\\\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\\\/#mainImage\"},\"datePublished\":\"2024-10-23T09:54:00+00:00\",\"dateModified\":\"2024-10-23T09:54:00+00:00\"},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/#website\",\"url\":\"https:\\\/\\\/sekuritasit.com\\\/\",\"name\":\"Sekuritas IT\",\"alternateName\":\"Sekuritas\",\"description\":\"Creative solutions to unique challenges.\",\"inLanguage\":\"en-US\",\"publisher\":{\"@id\":\"https:\\\/\\\/sekuritasit.com\\\/#organization\"}}]}\n\t\t<\/script>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"Researchers Reveal \u2018Deceptive Delight\u2019 Method to Jailbreak AI Models info@thehackernews.com (The Hacker News) \u203a Sekuritas IT","description":"Cybersecurity researchers have shed light on a new adversarial technique that could be used to jailbreak large language models (LLMs) during the course of an interactive conversation by sneaking in an undesirable instruction between benign ones. The approach has been codenamed Deceptive Delight by Palo Alto Networks Unit 42, which described it as both simple","canonical_url":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"BlogPosting","@id":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/#blogposting","name":"Researchers Reveal \u2018Deceptive Delight\u2019 Method to Jailbreak AI Models info@thehackernews.com (The Hacker News) \u203a Sekuritas IT","headline":"Researchers Reveal &#8216;Deceptive Delight&#8217; Method to Jailbreak AI Models info@thehackernews.com (The Hacker News)","author":{"@id":"https:\/\/sekuritasit.com\/index.php\/author\/#author"},"publisher":{"@id":"https:\/\/sekuritasit.com\/#organization"},"image":{"@type":"ImageObject","url":"https:\/\/sekuritasit.com\/wp-content\/uploads\/2024\/10\/ai-jailbreak-f8rEk8.png","width":728,"height":380},"datePublished":"2024-10-23T09:54:00+00:00","dateModified":"2024-10-23T09:54:00+00:00","inLanguage":"en-US","mainEntityOfPage":{"@id":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/#webpage"},"isPartOf":{"@id":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/#webpage"},"articleSection":"Uncategorized"},{"@type":"BreadcrumbList","@id":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/#breadcrumblist","itemListElement":[{"@type":"ListItem","@id":"https:\/\/sekuritasit.com#listItem","position":1,"name":"Home","item":"https:\/\/sekuritasit.com","nextItem":{"@type":"ListItem","@id":"https:\/\/sekuritasit.com\/index.php\/category\/uncategorized\/#listItem","name":"Uncategorized"}},{"@type":"ListItem","@id":"https:\/\/sekuritasit.com\/index.php\/category\/uncategorized\/#listItem","position":2,"name":"Uncategorized","item":"https:\/\/sekuritasit.com\/index.php\/category\/uncategorized\/","nextItem":{"@type":"ListItem","@id":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/#listItem","name":"Researchers Reveal &#8216;Deceptive Delight&#8217; Method to Jailbreak AI Models info@thehackernews.com (The Hacker News)"},"previousItem":{"@type":"ListItem","@id":"https:\/\/sekuritasit.com#listItem","name":"Home"}},{"@type":"ListItem","@id":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/#listItem","position":3,"name":"Researchers Reveal &#8216;Deceptive Delight&#8217; Method to Jailbreak AI Models info@thehackernews.com (The Hacker News)","previousItem":{"@type":"ListItem","@id":"https:\/\/sekuritasit.com\/index.php\/category\/uncategorized\/#listItem","name":"Uncategorized"}}]},{"@type":"Organization","@id":"https:\/\/sekuritasit.com\/#organization","name":"Sekuritas IT","description":"Creative solutions to unique challenges.","url":"https:\/\/sekuritasit.com\/","sameAs":["https:\/\/www.facebook.com\/profile.php?id=100086973577423"]},{"@type":"WebPage","@id":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/#webpage","url":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/","name":"Researchers Reveal \u2018Deceptive Delight\u2019 Method to Jailbreak AI Models info@thehackernews.com (The Hacker News) \u203a Sekuritas IT","description":"Cybersecurity researchers have shed light on a new adversarial technique that could be used to jailbreak large language models (LLMs) during the course of an interactive conversation by sneaking in an undesirable instruction between benign ones. The approach has been codenamed Deceptive Delight by Palo Alto Networks Unit 42, which described it as both simple","inLanguage":"en-US","isPartOf":{"@id":"https:\/\/sekuritasit.com\/#website"},"breadcrumb":{"@id":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/#breadcrumblist"},"author":{"@id":"https:\/\/sekuritasit.com\/index.php\/author\/#author"},"creator":{"@id":"https:\/\/sekuritasit.com\/index.php\/author\/#author"},"image":{"@type":"ImageObject","url":"https:\/\/sekuritasit.com\/wp-content\/uploads\/2024\/10\/ai-jailbreak-f8rEk8.png","@id":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/#mainImage","width":728,"height":380},"primaryImageOfPage":{"@id":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/#mainImage"},"datePublished":"2024-10-23T09:54:00+00:00","dateModified":"2024-10-23T09:54:00+00:00"},{"@type":"WebSite","@id":"https:\/\/sekuritasit.com\/#website","url":"https:\/\/sekuritasit.com\/","name":"Sekuritas IT","alternateName":"Sekuritas","description":"Creative solutions to unique challenges.","inLanguage":"en-US","publisher":{"@id":"https:\/\/sekuritasit.com\/#organization"}}]},"og:locale":"en_US","og:site_name":"Sekuritas IT \u203a Creative solutions to unique challenges.","og:type":"article","og:title":"Researchers Reveal \u2018Deceptive Delight\u2019 Method to Jailbreak AI Models info@thehackernews.com (The Hacker News) \u203a Sekuritas IT","og:description":"Cybersecurity researchers have shed light on a new adversarial technique that could be used to jailbreak large language models (LLMs) during the course of an interactive conversation by sneaking in an undesirable instruction between benign ones. The approach has been codenamed Deceptive Delight by Palo Alto Networks Unit 42, which described it as both simple","og:url":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/","article:published_time":"2024-10-23T09:54:00+00:00","article:modified_time":"2024-10-23T09:54:00+00:00","article:publisher":"https:\/\/www.facebook.com\/profile.php?id=100086973577423","twitter:card":"summary_large_image","twitter:title":"Researchers Reveal \u2018Deceptive Delight\u2019 Method to Jailbreak AI Models info@thehackernews.com (The Hacker News) \u203a Sekuritas IT","twitter:description":"Cybersecurity researchers have shed light on a new adversarial technique that could be used to jailbreak large language models (LLMs) during the course of an interactive conversation by sneaking in an undesirable instruction between benign ones. The approach has been codenamed Deceptive Delight by Palo Alto Networks Unit 42, which described it as both simple"},"aioseo_meta_data":{"post_id":"13680","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":"default","schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"breadcrumb_settings":null,"limit_modified_date":false,"ai":null,"created":"2024-10-23 10:59:49","updated":"2025-10-15 12:28:28","seo_analyzer_scan_date":null},"aioseo_breadcrumb":"<div class=\"aioseo-breadcrumbs\"><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/sekuritasit.com\" title=\"Home\">Home<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">&raquo;<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/sekuritasit.com\/index.php\/category\/uncategorized\/\" title=\"Uncategorized\">Uncategorized<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">&raquo;<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\tResearchers Reveal \u2018Deceptive Delight\u2019 Method to Jailbreak AI Models info@thehackernews.com (The Hacker News)\n\t\t<\/span><\/div>","aioseo_breadcrumb_json":[{"label":"Home","link":"https:\/\/sekuritasit.com"},{"label":"Uncategorized","link":"https:\/\/sekuritasit.com\/index.php\/category\/uncategorized\/"},{"label":"Researchers Reveal &#8216;Deceptive Delight&#8217; Method to Jailbreak AI Models info@thehackernews.com (The Hacker News)","link":"https:\/\/sekuritasit.com\/index.php\/2024\/10\/23\/researchers-reveal-deceptive-delight-method-to-jailbreak-ai-models-infothehackernews-com-the-hacker-news\/"}],"_links":{"self":[{"href":"https:\/\/sekuritasit.com\/index.php\/wp-json\/wp\/v2\/posts\/13680","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sekuritasit.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/sekuritasit.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/sekuritasit.com\/index.php\/wp-json\/wp\/v2\/comments?post=13680"}],"version-history":[{"count":0,"href":"https:\/\/sekuritasit.com\/index.php\/wp-json\/wp\/v2\/posts\/13680\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/sekuritasit.com\/index.php\/wp-json\/wp\/v2\/media\/13681"}],"wp:attachment":[{"href":"https:\/\/sekuritasit.com\/index.php\/wp-json\/wp\/v2\/media?parent=13680"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sekuritasit.com\/index.php\/wp-json\/wp\/v2\/categories?post=13680"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sekuritasit.com\/index.php\/wp-json\/wp\/v2\/tags?post=13680"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}