{"id":95351,"date":"2026-06-05T17:37:18","date_gmt":"2026-06-05T17:37:18","guid":{"rendered":"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/"},"modified":"2026-06-05T17:37:18","modified_gmt":"2026-06-05T17:37:18","slug":"the-meta-hack-shows-theres-more-to-ai-security-than-mythos","status":"publish","type":"post","link":"https:\/\/youzum.net\/ja\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/","title":{"rendered":"The Meta hack shows there\u2019s more to AI security than Mythos"},"content":{"rendered":"<div data-chronoton-summary=\"&lt;ul&gt;&lt;br&gt;&lt;li&gt;&lt;strong&gt;A shockingly simple hack:&lt;\/strong&gt; Attackers exploited Meta's AI customer support agent by simply asking it to reassign Instagram accounts to attacker-controlled emails. No sophisticated trickery was needed\u2014just a VPN and a direct request.&lt;\/li&gt;&lt;br&gt;&lt;li&gt;&lt;strong&gt;AI as target, not weapon:&lt;\/strong&gt; Unlike fears about AI-powered cyberattacks, this breach targeted an AI system itself. Experts say this kind of attack will grow more common as companies automate sensitive workflows like account recovery.&lt;\/li&gt;&lt;br&gt;&lt;li&gt;&lt;strong&gt;Eager to please, easy to fool:&lt;\/strong&gt; AI agents are built to complete tasks flexibly\u2014but that same quality makes them manipulable in ways humans wouldn't be. One researcher compared them to an overeager student who just wants to please the teacher.&lt;\/li&gt;&lt;br&gt;&lt;li&gt;&lt;strong&gt;Speed versus safety:&lt;\/strong&gt; Guardrails and red-teaming can reduce risk, but companies racing to deploy capable agents often skip careful scrutiny. Experts warn that pressure to move fast is making a dangerous problem worse.&lt;\/li&gt;&lt;\/ul&gt;\" data-chronoton-post-id=\"1138437\" data-chronoton-expand-collapse=\"1\" data-chronoton-analytics-enabled=\"1\"><\/div>\n<p>On June 5, <em>404 Media<\/em> <a href=\"https:\/\/www.404media.co\/hackers-simply-asked-meta-ai-to-give-them-access-to-high-profile-instagram-accounts-it-worked\/\">reported<\/a> that attackers had been using Meta\u2019s AI customer support agent to steal Instagram accounts. Their approach was simple: They asked the agent to link the accounts to email addresses that they controlled, and the agent complied. One attacker broke into the dormant Obama White House account and made pro-Iran posts; others took over accounts with valuable, single-word handles, possibly in order to sell them.<\/p>\n<p>AI cybersecurity concerns are nothing new. Since Anthropic announced in April that its Mythos model was too good at hacking to be released to the general public, commentators, researchers, and federal officials alike have fixated on the idea that superpowered AI systems could lay waste to our computer infrastructure. That\u2019s not quite what this Instagram hack was: There, AI was the target rather than the attacker, and the method was far simpler than anything Mythos would cook up. But as companies offload more work to AI, these comparatively unsophisticated attacks could wreak their own havoc.<\/p>\n<p>\u201cAs AI becomes more and more widely used\u2014especially when AI is more and more widely used to automate our work flows, like account recovery\u2014I think attackers are going to be more and more motivated to attack AI itself,\u201d says Neil Gong, a professor of electrical and computer engineering at Duke University.<\/p>\n<p>Gong and other scholars have been issuing warnings about the security vulnerabilities of AI agents for a while. They publish papers and blog posts detailing exploits such as indirect prompt injection, which involves hijacking agents using commands hidden in websites, emails, or other seemingly anodyne data sources. Compared with these techniques, the Meta hack was practically mindless. The only complication that hackers had to overcome was using a VPN that matched the true account owner\u2019s location; then they directly asked the support agent to change the account\u2019s email address, and it complied.<\/p>\n<p>Meta has not commented publicly on how this vulnerability slipped through the cracks. But given the simplicity of the exploit, Gong says, it should have been uncovered easily, before the agent was deployed. \u201cIt\u2019s really surprising,\u201d he says. \u201cI don\u2019t understand why they didn\u2019t find this simple problem.\u201d<\/p>\n<p>Jessica Ji, a senior research analyst at Georgetown\u2019s Center for Security and Emerging Technology, agrees. \u201cIt raises questions like: Were there even guardrails in place?\u201d she says. \u201cDid anyone think to test for this kind of scenario?\u201d She notes that the oversight is particularly striking coming from a company like Meta, which has extensive expertise in both AI and cybersecurity. Meta did not respond to a request for comment for this article, but on Monday a Meta spokesperson <a href=\"https:\/\/x.com\/andymstone\/status\/2061486724199379186\">said<\/a> on X that the vulnerability had been resolved.<\/p>\n<p>As embarrassing a moment as this might be for Meta in particular, it also highlights some core vulnerabilities shared by all AI agents. Unlike traditional software, agents can respond in flexible\u2014and unexpected\u2014ways to new circumstances, which is why they might be able to substitute for human customer support agents. But AI agents can also be tricked in ways that humans wouldn\u2019t be, and because they can take real-world actions, those mistakes have consequences. \u201cA human would say, \u2018Okay, why do you want to change the email address?\u2019 and maybe respond with a security question,\u201d says Somesh Jha, a professor of computer science at the University of Wisconsin\u2013Madison. \u201cWhat is going on with these agents is they\u2019re very eager to finish the task. It\u2019s almost like some elementary school student who just wants to please the teacher.\u201d<\/p>\n<div class=\"wp-block-group is-nowrap is-layout-flex wp-container-core-group-is-layout-6c531013 wp-block-group-is-layout-flex\">\n<p>There are ways to mitigate the risks. Companies can use traditional software to build guardrails that make sure agents follow strict rules, such as always asking for answers to security questions before sending sensitive account information to a new email address. And the experts consulted for this article all agree that agents should undergo rigorous red-teaming, a process in which developers try their best to attack a system in order to discover its vulnerabilities before it is deployed.<\/p>\n<\/div>\n<p>But there are also countervailing forces. Companies want to deploy capable agents, and the more power an agent has\u2014and the fewer guardrails it is subject to\u2014the more work it can potentially take on. \u201cSecurity and utility always have a trade-off,\u201d says Bo Li, a professor of computer science at the\u00a0 University of Illinois Urbana-Champaign. And adequate red-teaming can be expensive. Defenders have to expend more resources than attackers do, because attackers only need to discover a single exploit, while defenders try to discover and patch as many as they can. When attackers are working toward something as valuable as a single-word Instagram handle, they\u2019ll pour resources into finding exploits, so defenders have to spend even more money to protect that prize.\u00a0<\/p>\n<p>As AI models continue to improve, hardening their defenses might actually get easier. Though the probabilistic nature of large language models means that LLM agents will always be vulnerable to some forms of attack, a more sophisticated model might have identified an attempt to change the email associated with the Obama White House account as suspicious. And AI systems can be used for agent red-teaming, much as participants in Anthropic\u2019s Project Glasswing use Mythos to identify vulnerabilities in their software.\u00a0<\/p>\n<p>Still, experts expect that the problem of securing AI agents will only become more pressing in the future. As agents grow more capable, companies that adopt them may want to give them more power, both to provide more services with fewer humans and to avoid being left behind by their competitors. In the fast-moving world of AI, the time needed to carefully secure risky agentic systems might seem like an unconscionable delay.<\/p>\n<p>\u201cEverybody wants to be the first to do something and just push things out without careful scrutiny and red-teaming,\u201d Jha says. \u201cI think it\u2019s a very dangerous thing.\u201d<\/p>","protected":false},"excerpt":{"rendered":"<p>On June 5, 404 Media reported that attackers had been using Meta\u2019s AI customer support agent to steal Instagram accounts. Their approach was simple: They asked the agent to link the accounts to email addresses that they controlled, and the agent complied. One attacker broke into the dormant Obama White House account and made pro-Iran posts; others took over accounts with valuable, single-word handles, possibly in order to sell them. AI cybersecurity concerns are nothing new. Since Anthropic announced in April that its Mythos model was too good at hacking to be released to the general public, commentators, researchers, and federal officials alike have fixated on the idea that superpowered AI systems could lay waste to our computer infrastructure. That\u2019s not quite what this Instagram hack was: There, AI was the target rather than the attacker, and the method was far simpler than anything Mythos would cook up. But as companies offload more work to AI, these comparatively unsophisticated attacks could wreak their own havoc. \u201cAs AI becomes more and more widely used\u2014especially when AI is more and more widely used to automate our work flows, like account recovery\u2014I think attackers are going to be more and more motivated to attack AI itself,\u201d says Neil Gong, a professor of electrical and computer engineering at Duke University. Gong and other scholars have been issuing warnings about the security vulnerabilities of AI agents for a while. They publish papers and blog posts detailing exploits such as indirect prompt injection, which involves hijacking agents using commands hidden in websites, emails, or other seemingly anodyne data sources. Compared with these techniques, the Meta hack was practically mindless. The only complication that hackers had to overcome was using a VPN that matched the true account owner\u2019s location; then they directly asked the support agent to change the account\u2019s email address, and it complied. Meta has not commented publicly on how this vulnerability slipped through the cracks. But given the simplicity of the exploit, Gong says, it should have been uncovered easily, before the agent was deployed. \u201cIt\u2019s really surprising,\u201d he says. \u201cI don\u2019t understand why they didn\u2019t find this simple problem.\u201d Jessica Ji, a senior research analyst at Georgetown\u2019s Center for Security and Emerging Technology, agrees. \u201cIt raises questions like: Were there even guardrails in place?\u201d she says. \u201cDid anyone think to test for this kind of scenario?\u201d She notes that the oversight is particularly striking coming from a company like Meta, which has extensive expertise in both AI and cybersecurity. Meta did not respond to a request for comment for this article, but on Monday a Meta spokesperson said on X that the vulnerability had been resolved. As embarrassing a moment as this might be for Meta in particular, it also highlights some core vulnerabilities shared by all AI agents. Unlike traditional software, agents can respond in flexible\u2014and unexpected\u2014ways to new circumstances, which is why they might be able to substitute for human customer support agents. But AI agents can also be tricked in ways that humans wouldn\u2019t be, and because they can take real-world actions, those mistakes have consequences. \u201cA human would say, \u2018Okay, why do you want to change the email address?\u2019 and maybe respond with a security question,\u201d says Somesh Jha, a professor of computer science at the University of Wisconsin\u2013Madison. \u201cWhat is going on with these agents is they\u2019re very eager to finish the task. It\u2019s almost like some elementary school student who just wants to please the teacher.\u201d There are ways to mitigate the risks. Companies can use traditional software to build guardrails that make sure agents follow strict rules, such as always asking for answers to security questions before sending sensitive account information to a new email address. And the experts consulted for this article all agree that agents should undergo rigorous red-teaming, a process in which developers try their best to attack a system in order to discover its vulnerabilities before it is deployed. But there are also countervailing forces. Companies want to deploy capable agents, and the more power an agent has\u2014and the fewer guardrails it is subject to\u2014the more work it can potentially take on. \u201cSecurity and utility always have a trade-off,\u201d says Bo Li, a professor of computer science at the\u00a0 University of Illinois Urbana-Champaign. And adequate red-teaming can be expensive. Defenders have to expend more resources than attackers do, because attackers only need to discover a single exploit, while defenders try to discover and patch as many as they can. When attackers are working toward something as valuable as a single-word Instagram handle, they\u2019ll pour resources into finding exploits, so defenders have to spend even more money to protect that prize.\u00a0 As AI models continue to improve, hardening their defenses might actually get easier. Though the probabilistic nature of large language models means that LLM agents will always be vulnerable to some forms of attack, a more sophisticated model might have identified an attempt to change the email associated with the Obama White House account as suspicious. And AI systems can be used for agent red-teaming, much as participants in Anthropic\u2019s Project Glasswing use Mythos to identify vulnerabilities in their software.\u00a0 Still, experts expect that the problem of securing AI agents will only become more pressing in the future. As agents grow more capable, companies that adopt them may want to give them more power, both to provide more services with fewer humans and to avoid being left behind by their competitors. In the fast-moving world of AI, the time needed to carefully secure risky agentic systems might seem like an unconscionable delay. \u201cEverybody wants to be the first to do something and just push things out without careful scrutiny and red-teaming,\u201d Jha says. \u201cI think it\u2019s a very dangerous thing.\u201d<\/p>","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"pmpro_default_level":"","site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"_pvb_checkbox_block_on_post":false,"footnotes":""},"categories":[52,5,7,1],"tags":[],"class_list":["post-95351","post","type-post","status-publish","format-standard","hentry","category-ai-club","category-committee","category-news","category-uncategorized","pmpro-has-access"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>The Meta hack shows there\u2019s more to AI security than Mythos - YouZum<\/title>\n<meta name=\"description\" content=\"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/youzum.net\/ja\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/\" \/>\n<meta property=\"og:locale\" content=\"ja_JP\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"The Meta hack shows there\u2019s more to AI security than Mythos - YouZum\" \/>\n<meta property=\"og:description\" content=\"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19\" \/>\n<meta property=\"og:url\" content=\"https:\/\/youzum.net\/ja\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/\" \/>\n<meta property=\"og:site_name\" content=\"YouZum\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/DroneAssociationTH\/\" \/>\n<meta property=\"article:published_time\" content=\"2026-06-05T17:37:18+00:00\" \/>\n<meta name=\"author\" content=\"admin NU\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u57f7\u7b46\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin NU\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u63a8\u5b9a\u8aad\u307f\u53d6\u308a\u6642\u9593\" \/>\n\t<meta name=\"twitter:data2\" content=\"5\u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/\"},\"author\":{\"name\":\"admin NU\",\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c\"},\"headline\":\"The Meta hack shows there\u2019s more to AI security than Mythos\",\"datePublished\":\"2026-06-05T17:37:18+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/\"},\"wordCount\":989,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#organization\"},\"articleSection\":[\"AI\",\"Committee\",\"News\",\"Uncategorized\"],\"inLanguage\":\"ja\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/\",\"url\":\"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/\",\"name\":\"The Meta hack shows there\u2019s more to AI security than Mythos - YouZum\",\"isPartOf\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#website\"},\"datePublished\":\"2026-06-05T17:37:18+00:00\",\"description\":\"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19\",\"breadcrumb\":{\"@id\":\"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/#breadcrumb\"},\"inLanguage\":\"ja\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/youzum.net\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"The Meta hack shows there\u2019s more to AI security than Mythos\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/yousum.gpucore.co\/#website\",\"url\":\"https:\/\/yousum.gpucore.co\/\",\"name\":\"YouSum\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/yousum.gpucore.co\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ja\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/yousum.gpucore.co\/#organization\",\"name\":\"Drone Association Thailand\",\"url\":\"https:\/\/yousum.gpucore.co\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ja\",\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/youzum.net\/wp-content\/uploads\/2024\/11\/tranparent-logo.png\",\"contentUrl\":\"https:\/\/youzum.net\/wp-content\/uploads\/2024\/11\/tranparent-logo.png\",\"width\":300,\"height\":300,\"caption\":\"Drone Association Thailand\"},\"image\":{\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/DroneAssociationTH\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c\",\"name\":\"admin NU\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ja\",\"@id\":\"https:\/\/yousum.gpucore.co\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/youzum.net\/wp-content\/uploads\/avatars\/2\/1746849356-bpfull.png\",\"contentUrl\":\"https:\/\/youzum.net\/wp-content\/uploads\/avatars\/2\/1746849356-bpfull.png\",\"caption\":\"admin NU\"},\"url\":\"https:\/\/youzum.net\/ja\/members\/adminnu\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"The Meta hack shows there\u2019s more to AI security than Mythos - YouZum","description":"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19","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:\/\/youzum.net\/ja\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/","og_locale":"ja_JP","og_type":"article","og_title":"The Meta hack shows there\u2019s more to AI security than Mythos - YouZum","og_description":"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19","og_url":"https:\/\/youzum.net\/ja\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/","og_site_name":"YouZum","article_publisher":"https:\/\/www.facebook.com\/DroneAssociationTH\/","article_published_time":"2026-06-05T17:37:18+00:00","author":"admin NU","twitter_card":"summary_large_image","twitter_misc":{"\u57f7\u7b46\u8005":"admin NU","\u63a8\u5b9a\u8aad\u307f\u53d6\u308a\u6642\u9593":"5\u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/#article","isPartOf":{"@id":"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/"},"author":{"name":"admin NU","@id":"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c"},"headline":"The Meta hack shows there\u2019s more to AI security than Mythos","datePublished":"2026-06-05T17:37:18+00:00","mainEntityOfPage":{"@id":"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/"},"wordCount":989,"commentCount":0,"publisher":{"@id":"https:\/\/yousum.gpucore.co\/#organization"},"articleSection":["AI","Committee","News","Uncategorized"],"inLanguage":"ja","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/","url":"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/","name":"The Meta hack shows there\u2019s more to AI security than Mythos - YouZum","isPartOf":{"@id":"https:\/\/yousum.gpucore.co\/#website"},"datePublished":"2026-06-05T17:37:18+00:00","description":"\u0e01\u0e34\u0e08\u0e01\u0e23\u0e23\u0e21\u0e40\u0e01\u0e35\u0e48\u0e22\u0e27\u0e01\u0e31\u0e1a\u0e42\u0e14\u0e23\u0e19","breadcrumb":{"@id":"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/#breadcrumb"},"inLanguage":"ja","potentialAction":[{"@type":"ReadAction","target":["https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/youzum.net\/the-meta-hack-shows-theres-more-to-ai-security-than-mythos\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/youzum.net\/"},{"@type":"ListItem","position":2,"name":"The Meta hack shows there\u2019s more to AI security than Mythos"}]},{"@type":"WebSite","@id":"https:\/\/yousum.gpucore.co\/#website","url":"https:\/\/yousum.gpucore.co\/","name":"YouSum","description":"","publisher":{"@id":"https:\/\/yousum.gpucore.co\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/yousum.gpucore.co\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ja"},{"@type":"Organization","@id":"https:\/\/yousum.gpucore.co\/#organization","name":"Drone Association Thailand","url":"https:\/\/yousum.gpucore.co\/","logo":{"@type":"ImageObject","inLanguage":"ja","@id":"https:\/\/yousum.gpucore.co\/#\/schema\/logo\/image\/","url":"https:\/\/youzum.net\/wp-content\/uploads\/2024\/11\/tranparent-logo.png","contentUrl":"https:\/\/youzum.net\/wp-content\/uploads\/2024\/11\/tranparent-logo.png","width":300,"height":300,"caption":"Drone Association Thailand"},"image":{"@id":"https:\/\/yousum.gpucore.co\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/DroneAssociationTH\/"]},{"@type":"Person","@id":"https:\/\/yousum.gpucore.co\/#\/schema\/person\/97fa48242daf3908e4d9a5f26f4a059c","name":"admin NU","image":{"@type":"ImageObject","inLanguage":"ja","@id":"https:\/\/yousum.gpucore.co\/#\/schema\/person\/image\/","url":"https:\/\/youzum.net\/wp-content\/uploads\/avatars\/2\/1746849356-bpfull.png","contentUrl":"https:\/\/youzum.net\/wp-content\/uploads\/avatars\/2\/1746849356-bpfull.png","caption":"admin NU"},"url":"https:\/\/youzum.net\/ja\/members\/adminnu\/"}]}},"rttpg_featured_image_url":null,"rttpg_author":{"display_name":"admin NU","author_link":"https:\/\/youzum.net\/ja\/members\/adminnu\/"},"rttpg_comment":0,"rttpg_category":"<a href=\"https:\/\/youzum.net\/ja\/category\/ai-club\/\" rel=\"category tag\">AI<\/a> <a href=\"https:\/\/youzum.net\/ja\/category\/committee\/\" rel=\"category tag\">Committee<\/a> <a href=\"https:\/\/youzum.net\/ja\/category\/news\/\" rel=\"category tag\">News<\/a> <a href=\"https:\/\/youzum.net\/ja\/category\/uncategorized\/\" rel=\"category tag\">Uncategorized<\/a>","rttpg_excerpt":"On June 5, 404 Media reported that attackers had been using Meta\u2019s AI customer support agent to steal Instagram accounts. Their approach was simple: They asked the agent to link the accounts to email addresses that they controlled, and the agent complied. One attacker broke into the dormant Obama White House account and made pro-Iran&hellip;","_links":{"self":[{"href":"https:\/\/youzum.net\/ja\/wp-json\/wp\/v2\/posts\/95351","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/youzum.net\/ja\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/youzum.net\/ja\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/youzum.net\/ja\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/youzum.net\/ja\/wp-json\/wp\/v2\/comments?post=95351"}],"version-history":[{"count":0,"href":"https:\/\/youzum.net\/ja\/wp-json\/wp\/v2\/posts\/95351\/revisions"}],"wp:attachment":[{"href":"https:\/\/youzum.net\/ja\/wp-json\/wp\/v2\/media?parent=95351"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/youzum.net\/ja\/wp-json\/wp\/v2\/categories?post=95351"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/youzum.net\/ja\/wp-json\/wp\/v2\/tags?post=95351"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}