{"id":78850,"date":"2024-09-03T08:28:09","date_gmt":"2024-09-03T11:28:09","guid":{"rendered":"https:\/\/abes.org.br\/?p=78850"},"modified":"2024-08-16T17:35:01","modified_gmt":"2024-08-16T20:35:01","slug":"red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura","status":"publish","type":"post","link":"https:\/\/abes.org.br\/en\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/","title":{"rendered":"Red Teams Think Like Hackers to Help Keep AI Safe"},"content":{"rendered":"<div>\n<div>\n<p>Just as AI tools like ChatGPT and Copilot have transformed the way people work in all kinds of roles around the world, they\u2019ve also reshaped what\u2019s known as \u201cred teams.\u201d These are groups of cybersecurity experts who think like hackers to help keep technology safe and secure.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-78851 alignright\" src=\"https:\/\/abes.org.br\/wp-content\/uploads\/2024\/08\/microsoft.jpg\" alt=\"\" width=\"392\" height=\"220\" \/>Generative AI\u2019s ability to communicate in multiple languages, write stories, and even create photorealistic images introduces new potential risks. These range from providing biased or inaccurate results to giving attackers new ways to stir up discord. These new risks have prompted a different and broader approach to how Microsoft\u2019s AI Red Team needs to work to identify and mitigate potential harm.<\/p>\n<p>\u201cWe believe that safety, responsible AI, and the broader notion of AI security are different sides of the same coin,\u201d says Ram Shankar Siva Kumar, principal research leader at Microsoft. \u201cIt\u2019s important to have a comprehensive and comprehensive view of all the risks of an AI system before it reaches a customer\u2019s hands. This is an area that will have massive sociotechnical implications.\u201d<\/p>\n<p>The term \u201cred teaming\u201d was coined during the Cold War, when the U.S. Department of Defense conducted simulation exercises with \u201cred teams\u201d that played the Soviets and \u201cblue teams\u201d that played the U.S. and its allies. The cybersecurity community then adopted the language a few decades ago, creating red teams to act as adversaries trying to break, corrupt, or misuse technology\u2014with the ultimate goal of finding and fixing potential damage before real problems arise.<\/p>\n<p>When Siva Kumar formed Microsoft\u2019s AI Red Team in 2019, he followed the traditional model of bringing together cybersecurity experts to proactively investigate weaknesses, much like the company already does with all its products and services.<\/p>\n<p>At the same time, Forough Poursabzi was leading researchers across the company in studies that took a new angle and a different lens on responsible AI, now looking at whether generative technology could be harmful\u2014either intentionally or due to systemic issues in models that were overlooked during their training and evaluation. This is not something red teams have had to deal with before.<\/p>\n<p>The different groups quickly realized that they would be stronger together and joined forces to create a broader red team capable of assessing security risks and social harms side by side, adding to the team a neuroscientist, a linguist, a national security expert, and several other experts from diverse backgrounds and different fields.<\/p>\n<p>\u201cWe need a broad range of perspectives to do a responsible AI Red Team well,\u201d says Poursabzi, senior program manager on the AI Ethics and Effects team in Engineering and Research (Aether) at Microsoft. This team explores the entire responsible AI ecosystem at Microsoft and analyzes emerging risks and long-term considerations for generative AI technologies.<\/p>\n<p>The dedicated AI Red Team, led by Siva Kumar, is separate from those building the technology. Its expanded scope includes adversaries who might try to force a system to generate\u00a0<a href=\"https:\/\/news.microsoft.com\/source\/features\/ai\/why-ai-sometimes-gets-it-wrong-and-big-strides-to-address-it\/\" target=\"_blank\" rel=\"noopener\" data-saferedirecturl=\"https:\/\/www.google.com\/url?q=https:\/\/news.microsoft.com\/source\/features\/ai\/why-ai-sometimes-gets-it-wrong-and-big-strides-to-address-it\/&amp;source=gmail&amp;ust=1723903935566000&amp;usg=AOvVaw3ktuWzu_WMgOZx4i6MO_-_\">hallucinations<\/a>, as well as harmful, offensive or biased results, all due to inadequate or inaccurate data.<\/p>\n<p>Team members take on a variety of personas, from a creative teenager playing a prank to a familiar adversary trying to steal data, to uncover blind spots and uncover risks. Team members live around the world and collectively speak 17 languages, from Flemish to Mongolian to Telugu, to help with the diverse cultural contexts and threats specific to each region.<\/p>\n<p>And they don&#039;t just try to compromise systems alone \u2013 they use large language models (LLMs) for automated attacks on other LLMs.<\/p>\n<p>The group has further expanded the depth of its expertise by releasing open source frameworks such as\u00a0<a href=\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2023\/03\/02\/new-research-tooling-and-partnerships-for-more-secure-ai-and-machine-learning\/\" target=\"_blank\" rel=\"noopener\" data-saferedirecturl=\"https:\/\/www.google.com\/url?q=https:\/\/www.microsoft.com\/en-us\/security\/blog\/2023\/03\/02\/new-research-tooling-and-partnerships-for-more-secure-ai-and-machine-learning\/&amp;source=gmail&amp;ust=1723903935566000&amp;usg=AOvVaw0qYOVSZHtoYekxjCQx6Ft_\">the Counterfit<\/a>\u00a0and the Python Risk Identification Toolkit for generative AI, or\u00a0<a href=\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2024\/02\/22\/announcing-microsofts-open-automation-framework-to-red-team-generative-ai-systems\/\" target=\"_blank\" rel=\"noopener\" data-saferedirecturl=\"https:\/\/www.google.com\/url?q=https:\/\/www.microsoft.com\/en-us\/security\/blog\/2024\/02\/22\/announcing-microsofts-open-automation-framework-to-red-team-generative-ai-systems\/&amp;source=gmail&amp;ust=1723903935566000&amp;usg=AOvVaw3bSe4-hqMTXiXIp2l732f5\">PyRIT<\/a>, earlier this year. They are designed to help security professionals and machine learning engineers working outside the enterprise map potential risks. The tools help red team specialists \u2013 a limited resource \u2013 be more efficient and productive. The team published\u00a0<a href=\"https:\/\/learn.microsoft.com\/en-us\/azure\/ai-services\/openai\/concepts\/red-teaming\" target=\"_blank\" rel=\"noopener\" data-saferedirecturl=\"https:\/\/www.google.com\/url?q=https:\/\/learn.microsoft.com\/en-us\/azure\/ai-services\/openai\/concepts\/red-teaming&amp;source=gmail&amp;ust=1723903935566000&amp;usg=AOvVaw337Mb94oYl2ovApcpiMfi-\">best practices<\/a>\u00a0from your experiences to help others get started.<\/p>\n<p>Once Microsoft\u2019s AI Red Team finds an issue, it sends it to the responsible AI measurement team, which assesses how much of a threat the issue poses. Other experts and internal groups then address the issue to complete the three-step approach to safe AI: mapping, measuring, and managing risks.<\/p>\n<p>\u201cOur practice covers a wide range of harms that we try to prove,\u201d says Siva Kumar. \u201cWe adapt and retool quickly, and that has been the recipe for our success\u2014not waiting for the forces of change to mount, but anticipating them.\u201d<\/p>\n<p>Learn more about\u00a0<a href=\"https:\/\/www.microsoft.com\/en-us\/ai\/responsible-ai\" target=\"_blank\" rel=\"noopener\" data-saferedirecturl=\"https:\/\/www.google.com\/url?q=https:\/\/www.microsoft.com\/en-us\/ai\/responsible-ai&amp;source=gmail&amp;ust=1723903935566000&amp;usg=AOvVaw0RJkYua5n63xhofE4VcMpi\">Microsoft&#039;s Responsible AI Work<\/a>.<\/p>\n<p><em>This post is part of Microsoft\u2019s Building AI Responsibly series, which explores key concerns around AI deployment and how the company is addressing them with its responsible AI practices and tools.<\/em><\/p>\n<\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>Assim como ferramentas de IA, a exemplo do ChatGPT e Copilot, transformaram a maneira como as pessoas trabalham em todos os tipos de fun\u00e7\u00f5es ao redor do mundo, elas tamb\u00e9m remodelaram os chamados \u201cred teams\u201d (equipes vermelhas, em tradu\u00e7\u00e3o livre). S\u00e3o grupos de especialistas em seguran\u00e7a cibern\u00e9tica que pensam como hackers para ajudar a manter [&hellip;]<\/p>\n","protected":false},"author":10,"featured_media":78851,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_et_pb_use_builder":"","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[39,19],"tags":[5924,5922,5923],"class_list":["post-78850","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-coluna-4","category-ultimas-noticias","tag-habilidades-da-ia","tag-ia-segura","tag-red-team-de-ia"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.3 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Red Teams pensam como hackers para ajudar a manter a IA segura - ABES<\/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:\/\/abes.org.br\/en\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Red Teams pensam como hackers para ajudar a manter a IA segura - ABES\" \/>\n<meta property=\"og:description\" content=\"Assim como ferramentas de IA, a exemplo do ChatGPT e Copilot, transformaram a maneira como as pessoas trabalham em todos os tipos de fun\u00e7\u00f5es ao redor do mundo, elas tamb\u00e9m remodelaram os chamados \u201cred teams\u201d (equipes vermelhas, em tradu\u00e7\u00e3o livre). S\u00e3o grupos de especialistas em seguran\u00e7a cibern\u00e9tica que pensam como hackers para ajudar a manter [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/abes.org.br\/en\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/\" \/>\n<meta property=\"og:site_name\" content=\"ABES\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/ABES.software\" \/>\n<meta property=\"article:published_time\" content=\"2024-09-03T11:28:09+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/abes.org.br\/wp-content\/uploads\/2024\/08\/microsoft.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"896\" \/>\n\t<meta property=\"og:image:height\" content=\"503\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Editor ABES\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@ABES_SOFTWARE\" \/>\n<meta name=\"twitter:site\" content=\"@ABES_SOFTWARE\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Editor ABES\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/abes.org.br\\\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/abes.org.br\\\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\\\/\"},\"author\":{\"name\":\"Editor ABES\",\"@id\":\"https:\\\/\\\/abes.org.br\\\/#\\\/schema\\\/person\\\/d65ed84c8883a123fe668129fd6a7ed3\"},\"headline\":\"Red Teams pensam como hackers para ajudar a manter a IA segura\",\"datePublished\":\"2024-09-03T11:28:09+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/abes.org.br\\\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\\\/\"},\"wordCount\":962,\"publisher\":{\"@id\":\"https:\\\/\\\/abes.org.br\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/abes.org.br\\\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/abes.org.br\\\/wp-content\\\/uploads\\\/2024\\\/08\\\/microsoft.jpg\",\"keywords\":[\"habilidades da IA\",\"IA segura\",\"Red Team de IA\"],\"articleSection\":[\"-Coluna 4\",\"\u00daltimas not\u00edcias\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/abes.org.br\\\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\\\/\",\"url\":\"https:\\\/\\\/abes.org.br\\\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\\\/\",\"name\":\"Red Teams pensam como hackers para ajudar a manter a IA segura - ABES\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/abes.org.br\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/abes.org.br\\\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/abes.org.br\\\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/abes.org.br\\\/wp-content\\\/uploads\\\/2024\\\/08\\\/microsoft.jpg\",\"datePublished\":\"2024-09-03T11:28:09+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/abes.org.br\\\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/abes.org.br\\\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/abes.org.br\\\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\\\/#primaryimage\",\"url\":\"https:\\\/\\\/abes.org.br\\\/wp-content\\\/uploads\\\/2024\\\/08\\\/microsoft.jpg\",\"contentUrl\":\"https:\\\/\\\/abes.org.br\\\/wp-content\\\/uploads\\\/2024\\\/08\\\/microsoft.jpg\",\"width\":896,\"height\":503},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/abes.org.br\\\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"In\u00edcio\",\"item\":\"https:\\\/\\\/abes.org.br\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Red Teams pensam como hackers para ajudar a manter a IA segura\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/abes.org.br\\\/#website\",\"url\":\"https:\\\/\\\/abes.org.br\\\/\",\"name\":\"ABES\",\"description\":\"Associa\u00e7\u00e3o Brasileira das Empresas de Software\",\"publisher\":{\"@id\":\"https:\\\/\\\/abes.org.br\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/abes.org.br\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/abes.org.br\\\/#organization\",\"name\":\"Associa\u00e7\u00e3o Brasileira das Empresas de Software\",\"url\":\"https:\\\/\\\/abes.org.br\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/abes.org.br\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/abes.org.br\\\/wp-content\\\/uploads\\\/2020\\\/09\\\/logo_abes_marca_d_tagline_horizontal_verde-amarelo_cmyk.png\",\"contentUrl\":\"https:\\\/\\\/abes.org.br\\\/wp-content\\\/uploads\\\/2020\\\/09\\\/logo_abes_marca_d_tagline_horizontal_verde-amarelo_cmyk.png\",\"width\":324,\"height\":70,\"caption\":\"Associa\u00e7\u00e3o Brasileira das Empresas de Software\"},\"image\":{\"@id\":\"https:\\\/\\\/abes.org.br\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/ABES.software\",\"https:\\\/\\\/x.com\\\/ABES_SOFTWARE\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/abes-software\\\/\",\"https:\\\/\\\/www.instagram.com\\\/abes_software\\\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/abes.org.br\\\/#\\\/schema\\\/person\\\/d65ed84c8883a123fe668129fd6a7ed3\",\"name\":\"Editor ABES\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/3b207abce016c5e2ad6bf38914af9ad16e277128bb9b06dabb05bc191f02d7fe?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/3b207abce016c5e2ad6bf38914af9ad16e277128bb9b06dabb05bc191f02d7fe?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/3b207abce016c5e2ad6bf38914af9ad16e277128bb9b06dabb05bc191f02d7fe?s=96&d=mm&r=g\",\"caption\":\"Editor ABES\"},\"url\":\"https:\\\/\\\/abes.org.br\\\/en\\\/author\\\/editor-abes\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Red Teams pensam como hackers para ajudar a manter a IA segura - ABES","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:\/\/abes.org.br\/en\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/","og_locale":"en_US","og_type":"article","og_title":"Red Teams pensam como hackers para ajudar a manter a IA segura - ABES","og_description":"Assim como ferramentas de IA, a exemplo do ChatGPT e Copilot, transformaram a maneira como as pessoas trabalham em todos os tipos de fun\u00e7\u00f5es ao redor do mundo, elas tamb\u00e9m remodelaram os chamados \u201cred teams\u201d (equipes vermelhas, em tradu\u00e7\u00e3o livre). S\u00e3o grupos de especialistas em seguran\u00e7a cibern\u00e9tica que pensam como hackers para ajudar a manter [&hellip;]","og_url":"https:\/\/abes.org.br\/en\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/","og_site_name":"ABES","article_publisher":"https:\/\/www.facebook.com\/ABES.software","article_published_time":"2024-09-03T11:28:09+00:00","og_image":[{"width":896,"height":503,"url":"https:\/\/abes.org.br\/wp-content\/uploads\/2024\/08\/microsoft.jpg","type":"image\/jpeg"}],"author":"Editor ABES","twitter_card":"summary_large_image","twitter_creator":"@ABES_SOFTWARE","twitter_site":"@ABES_SOFTWARE","twitter_misc":{"Written by":"Editor ABES","Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/abes.org.br\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/#article","isPartOf":{"@id":"https:\/\/abes.org.br\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/"},"author":{"name":"Editor ABES","@id":"https:\/\/abes.org.br\/#\/schema\/person\/d65ed84c8883a123fe668129fd6a7ed3"},"headline":"Red Teams pensam como hackers para ajudar a manter a IA segura","datePublished":"2024-09-03T11:28:09+00:00","mainEntityOfPage":{"@id":"https:\/\/abes.org.br\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/"},"wordCount":962,"publisher":{"@id":"https:\/\/abes.org.br\/#organization"},"image":{"@id":"https:\/\/abes.org.br\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/#primaryimage"},"thumbnailUrl":"https:\/\/abes.org.br\/wp-content\/uploads\/2024\/08\/microsoft.jpg","keywords":["habilidades da IA","IA segura","Red Team de IA"],"articleSection":["-Coluna 4","\u00daltimas not\u00edcias"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/abes.org.br\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/","url":"https:\/\/abes.org.br\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/","name":"Red Teams pensam como hackers para ajudar a manter a IA segura - ABES","isPartOf":{"@id":"https:\/\/abes.org.br\/#website"},"primaryImageOfPage":{"@id":"https:\/\/abes.org.br\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/#primaryimage"},"image":{"@id":"https:\/\/abes.org.br\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/#primaryimage"},"thumbnailUrl":"https:\/\/abes.org.br\/wp-content\/uploads\/2024\/08\/microsoft.jpg","datePublished":"2024-09-03T11:28:09+00:00","breadcrumb":{"@id":"https:\/\/abes.org.br\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/abes.org.br\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/abes.org.br\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/#primaryimage","url":"https:\/\/abes.org.br\/wp-content\/uploads\/2024\/08\/microsoft.jpg","contentUrl":"https:\/\/abes.org.br\/wp-content\/uploads\/2024\/08\/microsoft.jpg","width":896,"height":503},{"@type":"BreadcrumbList","@id":"https:\/\/abes.org.br\/red-teams-pensam-como-hackers-para-ajudar-a-manter-a-ia-segura\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"In\u00edcio","item":"https:\/\/abes.org.br\/"},{"@type":"ListItem","position":2,"name":"Red Teams pensam como hackers para ajudar a manter a IA segura"}]},{"@type":"WebSite","@id":"https:\/\/abes.org.br\/#website","url":"https:\/\/abes.org.br\/","name":"ABES","description":"Brazilian Association of Software Companies","publisher":{"@id":"https:\/\/abes.org.br\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/abes.org.br\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/abes.org.br\/#organization","name":"Brazilian Association of Software Companies","url":"https:\/\/abes.org.br\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/abes.org.br\/#\/schema\/logo\/image\/","url":"https:\/\/abes.org.br\/wp-content\/uploads\/2020\/09\/logo_abes_marca_d_tagline_horizontal_verde-amarelo_cmyk.png","contentUrl":"https:\/\/abes.org.br\/wp-content\/uploads\/2020\/09\/logo_abes_marca_d_tagline_horizontal_verde-amarelo_cmyk.png","width":324,"height":70,"caption":"Associa\u00e7\u00e3o Brasileira das Empresas de Software"},"image":{"@id":"https:\/\/abes.org.br\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/ABES.software","https:\/\/x.com\/ABES_SOFTWARE","https:\/\/www.linkedin.com\/company\/abes-software\/","https:\/\/www.instagram.com\/abes_software\/"]},{"@type":"Person","@id":"https:\/\/abes.org.br\/#\/schema\/person\/d65ed84c8883a123fe668129fd6a7ed3","name":"ABES Editor","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/3b207abce016c5e2ad6bf38914af9ad16e277128bb9b06dabb05bc191f02d7fe?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/3b207abce016c5e2ad6bf38914af9ad16e277128bb9b06dabb05bc191f02d7fe?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/3b207abce016c5e2ad6bf38914af9ad16e277128bb9b06dabb05bc191f02d7fe?s=96&d=mm&r=g","caption":"Editor ABES"},"url":"https:\/\/abes.org.br\/en\/author\/editor-abes\/"}]}},"publishpress_future_action":{"enabled":false,"date":"2026-04-10 20:15:57","action":"change-status","newStatus":"draft","terms":[],"taxonomy":"category","extraData":[]},"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/abes.org.br\/en\/wp-json\/wp\/v2\/posts\/78850","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/abes.org.br\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/abes.org.br\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/abes.org.br\/en\/wp-json\/wp\/v2\/users\/10"}],"replies":[{"embeddable":true,"href":"https:\/\/abes.org.br\/en\/wp-json\/wp\/v2\/comments?post=78850"}],"version-history":[{"count":2,"href":"https:\/\/abes.org.br\/en\/wp-json\/wp\/v2\/posts\/78850\/revisions"}],"predecessor-version":[{"id":78853,"href":"https:\/\/abes.org.br\/en\/wp-json\/wp\/v2\/posts\/78850\/revisions\/78853"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/abes.org.br\/en\/wp-json\/wp\/v2\/media\/78851"}],"wp:attachment":[{"href":"https:\/\/abes.org.br\/en\/wp-json\/wp\/v2\/media?parent=78850"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/abes.org.br\/en\/wp-json\/wp\/v2\/categories?post=78850"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/abes.org.br\/en\/wp-json\/wp\/v2\/tags?post=78850"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}