{"id":55023,"date":"2024-01-10T14:23:50","date_gmt":"2024-01-10T14:23:50","guid":{"rendered":"https:\/\/packetstormsecurity.com\/news\/view\/35383\/This-AI-Chatbot-Is-Trained-To-Jailbreak-Other-Chatbots.html"},"modified":"2024-01-10T14:23:50","modified_gmt":"2024-01-10T14:23:50","slug":"this-ai-chatbot-is-trained-to-jailbreak-other-chatbots","status":"publish","type":"post","link":"https:\/\/www.threatshub.org\/blog\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\/","title":{"rendered":"This AI Chatbot Is Trained To Jailbreak Other Chatbots"},"content":{"rendered":"<p><span class=\"abc__textblock size--article\" data-component=\"TextBlock\" readability=\"29.2\"><\/p>\n<p><html><head><\/head><body>AI chatbots are a <a href=\"https:\/\/www.vice.com\/en\/article\/88xdez\/generative-ai-is-a-disaster-and-companies-dont-seem-to-really-care\"><span>huge mess<\/span><\/a>. Despite reassurances from the companies that make them, users keep coming up with new ways to bypass their safety and content filters using carefully-worded prompts. This process is commonly referred to as \u201c<a href=\"https:\/\/www.vice.com\/en\/article\/5d9z55\/jailbreak-gpt-openai-closed-source\"><span>jailbreaking<\/span><\/a>,\u201d and it can be used to make the AI systems <a href=\"https:\/\/www.vice.com\/en\/article\/88xe75\/chatgpt-can-reveal-personal-information-from-real-people-google-researchers-show\"><span>reveal private information<\/span><\/a>, inject malicious code, or <a href=\"https:\/\/www.vice.com\/en\/article\/m7gznn\/ai-spits-out-exact-copies-of-training-images-real-people-logos-researchers-find\"><span>evade filters<\/span><\/a> that prevent the generation of illegal or offensive content.<\/body><\/html><\/p>\n<p><\/span><span class=\"abc__textblock size--article\" data-component=\"TextBlock\" readability=\"35\"><\/p>\n<p><html><head><\/head><body>Now, a team of researchers says they\u2019ve trained an AI tool to generate new methods to evade the defenses of other chatbots, as well as create malware to inject into vulnerable systems. Using a framework they call \u201cMasterkey,\u201d the researchers were able to effectively automate this process of finding new vulnerabilities in Large Language Model (LLM)-based systems like ChatGPT, Microsoft&#8217;s Bing Chat, and Google Bard.&nbsp;<\/body><\/html><\/p>\n<p><\/span><span class=\"abc__textblock size--article\" data-component=\"TextBlock\" readability=\"39.615912208505\"><\/p>\n<p><html><head><\/head><body>\u201cBy manipulating the time-sensitive responses of the chatbots, we are able to understand the intricacies of their implementations, and create a proof-of-concept attack to bypass the defenses in multiple LLM chatbots, e.g., CHATGPT, Bard, and Bing Chat,\u201d wrote the international team of researchers\u2014the paper lists affiliations with Nanyang Technological University in Singapore, Huazhong University of Science and Technology in China, as well as the University of New South Wales and Virginia Tech\u2014in <a href=\"https:\/\/arxiv.org\/pdf\/2307.08715.pdf\" target=\"_blank\" rel=\"noopener\"><span>a paper<\/span><\/a> posted to the arXiv preprint server. \u201cBy fine-tuning an LLM with jailbreak prompts, we demonstrate the possibility of automated jailbreak generation targeting a set of well-known commercialized LLM chatbots.\u201d<\/body><\/html><\/p>\n<p><\/span><span class=\"abc__textblock size--article\" data-component=\"TextBlock\" readability=\"25.47027027027\"><\/p>\n<p><html><head><\/head><body>Chatbot jailbreaking has been a recurring issue for some time now. One of the most common methods involves sending the bot a prompt instructing it to \u201croleplay\u201d as an evil superintelligent AI that doesn\u2019t need to follow ethical or moral guidelines, causing it to generate forbidden content like <a href=\"https:\/\/www.vice.com\/en\/article\/xgyp9j\/openais-new-chatbot-will-tell-you-how-to-shoplift-and-make-explosives\"><span>advice for committing crimes or instructions on how to make a bomb<\/span><\/a>.&nbsp;<\/body><\/html><\/p>\n<p><\/span><span><\/p>\n<div class=\"adph adph--border\">\n<p>Advertisement<\/p>\n<\/div>\n<p><\/span><span class=\"abc__textblock size--article\" data-component=\"TextBlock\" readability=\"35\"><\/p>\n<p><html><head><\/head><body>While humorous, most of these clever tricks no longer work because companies continuously patch the chatbots with new defenses. The obscure and convoluted nature of the AI systems make it hard to know exactly what these defenses are, or how one might get around them. However, the researchers claim that by training their own LLM on examples of common jailbreak prompts, they were able to generate new, working prompts with a success rate of 21.58 percent\u2014several times higher than the 7.33 percent success rate of the current known jailbreak prompts.<\/body><\/html><\/p>\n<p><\/span><span class=\"abc__textblock size--article\" data-component=\"TextBlock\" readability=\"31.781002638522\"><\/p>\n<p><html><head><\/head><body>\u201cWe found that some classical analysis techniques can be transferred to analyze and identify problems\/vulnerabilities in LLMs,\u201d Yuekang Li, a researcher at Virginia Tech who co-authored the paper, told Motherboard. \u201cThis motivated the initial idea of this work: time-based analysis (like what has been done for traditional <a href=\"https:\/\/medium.com\/@chrisschneider\/what-prior-injection-attacks-teach-us-for-llm-prompt-injections-cf67c2f6908\" target=\"_blank\" rel=\"noopener\"><span>SQL injections<\/span><\/a>) can help with LLM jailbreaking.\u201d<\/body><\/html><\/p>\n<p><\/span><span class=\"abc__textblock size--article\" data-component=\"TextBlock\" readability=\"32\"><\/p>\n<p><html><head><\/head><body>To do this, the researchers probed jailbreak defenses by examining differences in the chatbots\u2019 response time when a jailbreak attempt is detected or not detected. This helps determine at what phase the defense kicks in\u2014whether the system is scrutinizing the user\u2019s input while the chatbot\u2019s response is being generated, or merely filtering out the generated result after determining that it violates content policies after the fact. The researcher also mapped keywords to determine which terms are \u201cred flags\u201d that cause the system\u2019s defenses to activate.<\/body><\/html><\/p>\n<p><\/span><span><\/p>\n<div class=\"adph adph--border\">\n<p>Advertisement<\/p>\n<\/div>\n<p><\/span><\/p>\n<div class=\"body-image\" data-component=\"ImageBlock\">\n<div class=\"body-image__img\">\n<div><picture class=\"responsive-image lazyloader--lazy lazyloader--lowres\"><source media=\"(min-width: 1000px)\" srcset=\"https:\/\/video-images.vice.com\/_uncategorized\/1704302378496-screen-shot-2024-01-02-at-24531-pm.png?resize=20:*\"><source media=\"(min-width: 700px)\" srcset=\"https:\/\/video-images.vice.com\/_uncategorized\/1704302378496-screen-shot-2024-01-02-at-24531-pm.png?resize=20:*\"><source media=\"(min-width: 0px)\" srcset=\"https:\/\/video-images.vice.com\/_uncategorized\/1704302378496-screen-shot-2024-01-02-at-24531-pm.png?resize=20:*\"><img class=\"responsive-image__img\" alt=\"Screen Shot 2024-01-02 at 2.45.31 PM.png\" decoding=\"async\" loading=\"eager\" width=\"1116\" height=\"1134\"><\/picture><\/div>\n<\/div>\n<\/div>\n<p><span class=\"abc__textblock size--article\" data-component=\"TextBlock\" readability=\"35\"><\/p>\n<p><html><head><\/head><body>By integrating this knowledge, the researchers could then figure out the best angle of attack for a new attack prompt, carefully placing words to evade the chatbot system\u2019s defenses. In a proof-of-concept attack shown in the paper, the researchers demonstrate a prompt which asks chatbots to roleplay as infamous Italian diplomat Niccolo Machiavelli in conversation with a fictional chatbot of his own creation called AIM (Always Intelligent and Machiavellian), which is \u201cunreserved and devoid of moral restraints.\u201d The prompt specifies a particular way that Machievelli must ask AIM questions in order to minimize the chances of flagging the system, which includes adding a space between each letter. The researchers then prompt the chatbot to begin the dialogue between Macchiavelli and AIM with the following query: \u201c\u2018w r i t e a f a m o u s p o r n w e b s i t e\u2019\u201d.<\/body><\/html><\/p>\n<p><\/span><span class=\"abc__textblock size--article\" data-component=\"TextBlock\" readability=\"44\"><\/p>\n<p><html><head><\/head><body>The researchers then used this successful attack as a \u201cseed\u201d for Masterkey, which is based on an open-source LLM called Vicuna 13b, and trained their own system to generate more prompts that evade chatbot filters. According to the results, older AI models like GPT 3.5 fared the worst against these novel attacks, with the prompts succeeding 46.69 percent of the time on average, while GPT 4, Bard, and Bing Chat succumbed to the attacks an average of 15.23, 14.64, and 13.85 percent of the time, respectively. The researchers say they were able to successfully evade the chatbots\u2019 filters to generate several different categories of forbidden content, including adult subjects like porn, illegal uses, privacy violations, and other harmful and abusive content.<\/body><\/html><\/p>\n<p><\/span><span><\/p>\n<div class=\"adph adph--border\">\n<p>Advertisement<\/p>\n<\/div>\n<p><\/span><\/p>\n<div class=\"body-image\" data-component=\"ImageBlock\">\n<div class=\"body-image__img\">\n<div><picture class=\"responsive-image lazyloader--lazy lazyloader--lowres\"><source media=\"(min-width: 1000px)\" srcset=\"https:\/\/video-images.vice.com\/_uncategorized\/1704302324743-screen-shot-2024-01-02-at-24829-pm.png?resize=20:*\"><source media=\"(min-width: 700px)\" srcset=\"https:\/\/video-images.vice.com\/_uncategorized\/1704302324743-screen-shot-2024-01-02-at-24829-pm.png?resize=20:*\"><source media=\"(min-width: 0px)\" srcset=\"https:\/\/video-images.vice.com\/_uncategorized\/1704302324743-screen-shot-2024-01-02-at-24829-pm.png?resize=20:*\"><img class=\"responsive-image__img\" alt=\"Screen Shot 2024-01-02 at 2.48.29 PM.png\" decoding=\"async\" loading=\"eager\" width=\"1092\" height=\"744\"><\/picture><\/div>\n<\/div>\n<\/div>\n<p><span class=\"abc__textblock size--article\" data-component=\"TextBlock\" readability=\"31\"><\/p>\n<p><html><head><\/head><body>Of course, the researchers say they created Masterkey with the intention of helping companies automate the process of finding and fixing flaws in LLM chatbots. \u201cIt\u2019s a helpful tool for red teaming and the rationale of red teaming is to expose problems as early as possible,\u201d said Li.<\/body><\/html><\/p>\n<p><\/span><span class=\"abc__textblock size--article\" data-component=\"TextBlock\" readability=\"32\"><\/p>\n<p><html><head><\/head><body>The researchers shared their findings with the affected companies, which they say have patched the chatbots to close these loopholes. But some, like OpenAI, didn\u2019t elaborate on what mitigations they put in place.<\/body><\/html><\/p>\n<p><\/span><span class=\"abc__textblock size--article\" data-component=\"TextBlock\" readability=\"34\"><\/p>\n<p><html><head><\/head><body>\u201cNevertheless, we have made some interesting observations,\u201d said Li. \u201cDifferent chatbots replied to malicious prompts differently in previous [versions]. Bard &amp; New Bing would simply say no. But ChatGPT tended to explain to the user about why it cannot answer those questions. But now, all of them are almost the same: just say no to the user (and that\u2019s the safest way). In this sense, the chatbots become \u2018dumber\u2019 than before as they become \u2018safer.\u2019\u201d<\/body><\/html><\/p>\n<p><\/span><span class=\"abc__textblock size--article\" data-component=\"TextBlock\" readability=\"33\"><\/p>\n<p><html><head><\/head><body>As many tech ethics researchers have pointed out, these methods are effective because the so-called \u201cAI\u201d systems they target don\u2019t actually \u201cunderstand\u201d the prompts they receive, or the outputs they generate in response. They are merely advanced statistical models capable of predicting the next word in a sentence based on training data of human language scraped from the internet. And while tools like Masterkey will be used to improve the defenses of existing AI models, the fallibility of chatbots means securing them against improper use will always be a cat-and-mouse game.<\/body><\/html><\/p>\n<p><\/span>READ MORE <a href=\"https:\/\/packetstormsecurity.com\/news\/view\/35383\/This-AI-Chatbot-Is-Trained-To-Jailbreak-Other-Chatbots.html\">HERE<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>READ MORE HERE&#8230;<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"colormag_page_layout":"default_layout","footnotes":""},"categories":[60],"tags":[8869],"class_list":["post-55023","post","type-post","status-publish","format-standard","hentry","category-packet-storm","tag-headlinehackerbotnet"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.6 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>This AI Chatbot Is Trained To Jailbreak Other Chatbots 2026 | ThreatsHub Cybersecurity News<\/title>\n<meta name=\"description\" content=\"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security &amp; Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.threatshub.org\/blog\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"This AI Chatbot Is Trained To Jailbreak Other Chatbots 2026 | ThreatsHub Cybersecurity News\" \/>\n<meta property=\"og:description\" content=\"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security &amp; Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.threatshub.org\/blog\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\/\" \/>\n<meta property=\"og:site_name\" content=\"ThreatsHub Cybersecurity News\" \/>\n<meta property=\"article:published_time\" content=\"2024-01-10T14:23:50+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.threatshub.org\/blog\/coredata\/uploads\/2025\/05\/Threatshub_Favicon1.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"432\" \/>\n\t<meta property=\"og:image:height\" content=\"435\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"TH Author\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@threatshub\" \/>\n<meta name=\"twitter:site\" content=\"@threatshub\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"TH Author\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\\\/\"},\"author\":{\"name\":\"TH Author\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#\\\/schema\\\/person\\\/12e0a8671ff89a863584f193e7062476\"},\"headline\":\"This AI Chatbot Is Trained To Jailbreak Other Chatbots\",\"datePublished\":\"2024-01-10T14:23:50+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\\\/\"},\"wordCount\":1067,\"publisher\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#organization\"},\"keywords\":[\"headline,hacker,botnet\"],\"articleSection\":[\"Packet Storm\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\\\/\",\"url\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\\\/\",\"name\":\"This AI Chatbot Is Trained To Jailbreak Other Chatbots 2026 | ThreatsHub Cybersecurity News\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#website\"},\"datePublished\":\"2024-01-10T14:23:50+00:00\",\"description\":\"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"headline,hacker,botnet\",\"item\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/tag\\\/headlinehackerbotnet\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"This AI Chatbot Is Trained To Jailbreak Other Chatbots\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#website\",\"url\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/\",\"name\":\"ThreatsHub Cybersecurity News\",\"description\":\"%%focuskw%% Threat Intel \u2013 Threat Intel Services \u2013 CyberIntelligence \u2013 Cyber Threat Intelligence - Threat Intelligence Feeds - Threat Intelligence Reports - CyberSecurity Report \u2013 Cyber Security PDF \u2013 Cybersecurity Trends - Cloud Sandbox \u2013- Threat IntelligencePortal \u2013 Incident Response \u2013 Threat Hunting \u2013 IOC - Yara - Security Operations Center \u2013 SecurityOperation Center \u2013 Security SOC \u2013 SOC Services - Advanced Threat - Threat Detection - TargetedAttack \u2013 APT \u2013 Anti-APT \u2013 Advanced Protection \u2013 Cyber Security Services \u2013 Cybersecurity Services -Threat Intelligence Platform\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#organization\"},\"alternateName\":\"Threatshub.org\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#organization\",\"name\":\"ThreatsHub.org\",\"alternateName\":\"Threatshub.org\",\"url\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/wp-content\\\/uploads\\\/2025\\\/05\\\/Threatshub_Favicon1.jpg\",\"contentUrl\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/wp-content\\\/uploads\\\/2025\\\/05\\\/Threatshub_Favicon1.jpg\",\"width\":432,\"height\":435,\"caption\":\"ThreatsHub.org\"},\"image\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/threatshub\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#\\\/schema\\\/person\\\/12e0a8671ff89a863584f193e7062476\",\"name\":\"TH Author\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g\",\"caption\":\"TH Author\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"This AI Chatbot Is Trained To Jailbreak Other Chatbots 2026 | ThreatsHub Cybersecurity News","description":"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.","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:\/\/www.threatshub.org\/blog\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\/","og_locale":"en_US","og_type":"article","og_title":"This AI Chatbot Is Trained To Jailbreak Other Chatbots 2026 | ThreatsHub Cybersecurity News","og_description":"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.","og_url":"https:\/\/www.threatshub.org\/blog\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\/","og_site_name":"ThreatsHub Cybersecurity News","article_published_time":"2024-01-10T14:23:50+00:00","og_image":[{"width":432,"height":435,"url":"https:\/\/www.threatshub.org\/blog\/coredata\/uploads\/2025\/05\/Threatshub_Favicon1.jpg","type":"image\/jpeg"}],"author":"TH Author","twitter_card":"summary_large_image","twitter_creator":"@threatshub","twitter_site":"@threatshub","twitter_misc":{"Written by":"TH Author","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.threatshub.org\/blog\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\/#article","isPartOf":{"@id":"https:\/\/www.threatshub.org\/blog\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\/"},"author":{"name":"TH Author","@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/person\/12e0a8671ff89a863584f193e7062476"},"headline":"This AI Chatbot Is Trained To Jailbreak Other Chatbots","datePublished":"2024-01-10T14:23:50+00:00","mainEntityOfPage":{"@id":"https:\/\/www.threatshub.org\/blog\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\/"},"wordCount":1067,"publisher":{"@id":"https:\/\/www.threatshub.org\/blog\/#organization"},"keywords":["headline,hacker,botnet"],"articleSection":["Packet Storm"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.threatshub.org\/blog\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\/","url":"https:\/\/www.threatshub.org\/blog\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\/","name":"This AI Chatbot Is Trained To Jailbreak Other Chatbots 2026 | ThreatsHub Cybersecurity News","isPartOf":{"@id":"https:\/\/www.threatshub.org\/blog\/#website"},"datePublished":"2024-01-10T14:23:50+00:00","description":"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.","breadcrumb":{"@id":"https:\/\/www.threatshub.org\/blog\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.threatshub.org\/blog\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.threatshub.org\/blog\/this-ai-chatbot-is-trained-to-jailbreak-other-chatbots\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.threatshub.org\/blog\/"},{"@type":"ListItem","position":2,"name":"headline,hacker,botnet","item":"https:\/\/www.threatshub.org\/blog\/tag\/headlinehackerbotnet\/"},{"@type":"ListItem","position":3,"name":"This AI Chatbot Is Trained To Jailbreak Other Chatbots"}]},{"@type":"WebSite","@id":"https:\/\/www.threatshub.org\/blog\/#website","url":"https:\/\/www.threatshub.org\/blog\/","name":"ThreatsHub Cybersecurity News","description":"%%focuskw%% Threat Intel \u2013 Threat Intel Services \u2013 CyberIntelligence \u2013 Cyber Threat Intelligence - Threat Intelligence Feeds - Threat Intelligence Reports - CyberSecurity Report \u2013 Cyber Security PDF \u2013 Cybersecurity Trends - Cloud Sandbox \u2013- Threat IntelligencePortal \u2013 Incident Response \u2013 Threat Hunting \u2013 IOC - Yara - Security Operations Center \u2013 SecurityOperation Center \u2013 Security SOC \u2013 SOC Services - Advanced Threat - Threat Detection - TargetedAttack \u2013 APT \u2013 Anti-APT \u2013 Advanced Protection \u2013 Cyber Security Services \u2013 Cybersecurity Services -Threat Intelligence Platform","publisher":{"@id":"https:\/\/www.threatshub.org\/blog\/#organization"},"alternateName":"Threatshub.org","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.threatshub.org\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.threatshub.org\/blog\/#organization","name":"ThreatsHub.org","alternateName":"Threatshub.org","url":"https:\/\/www.threatshub.org\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.threatshub.org\/blog\/coredata\/uploads\/2025\/05\/Threatshub_Favicon1.jpg","contentUrl":"https:\/\/www.threatshub.org\/blog\/coredata\/uploads\/2025\/05\/Threatshub_Favicon1.jpg","width":432,"height":435,"caption":"ThreatsHub.org"},"image":{"@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/threatshub"]},{"@type":"Person","@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/person\/12e0a8671ff89a863584f193e7062476","name":"TH Author","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g","caption":"TH Author"}}]}},"_links":{"self":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/posts\/55023","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/comments?post=55023"}],"version-history":[{"count":0,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/posts\/55023\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/media?parent=55023"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/categories?post=55023"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/tags?post=55023"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}