{"id":3996,"date":"2024-02-17T08:46:48","date_gmt":"2024-02-17T00:46:48","guid":{"rendered":"https:\/\/www.1ai.net\/?p=3996"},"modified":"2024-02-17T08:46:48","modified_gmt":"2024-02-17T00:46:48","slug":"%e8%b0%b7%e6%ad%8c%e5%bc%80%e6%ba%90-magika%ef%bc%9a%e6%af%ab%e7%a7%92%e7%ba%a7%e8%af%86%e5%88%ab%e5%86%85%e5%ae%b9%e7%b1%bb%e5%9e%8b%ef%bc%8c%e7%99%be%e4%b8%87%e6%96%87%e4%bb%b6%e6%b5%8b%e8%af%95","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/3996.html","title":{"rendered":"Google open-sources Magika: millisecond-level content type recognition, with an accuracy rate of over 99% in a million file test"},"content":{"rendered":"<p data-vmark=\"d770\"><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%b0%b7%e6%ad%8c\" title=\"[View articles tagged with [Google]]\" target=\"_blank\" >Google<\/a>Recently updated the blog post, announcing<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%bc%80%e6%ba%90\" title=\"[View articles tagged with [open source]]\" target=\"_blank\" >Open Source<\/a> <a href=\"https:\/\/www.1ai.net\/en\/tag\/magika\" title=\"_Other Organiser\" target=\"_blank\" >Magika<\/a>,<strong>Based on artificial intelligence, it can quickly and efficiently identify file formats and content types. The relevant source code has been hosted on GitHub.<\/strong><\/p>\n<p data-vmark=\"82ca\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-3998\" title=\"2aae9fe3-0f1c-450e-93c0-bc64a6898438\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/02\/2aae9fe3-0f1c-450e-93c0-bc64a6898438.jpg\" alt=\"2aae9fe3-0f1c-450e-93c0-bc64a6898438\" width=\"1024\" height=\"559\" \/><\/p>\n<p data-vmark=\"c586\">Magika uses a custom, highly optimized deep learning model that can accurately identify file types in milliseconds even when running on a CPU.<\/p>\n<p data-vmark=\"f389\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-3997\" title=\"9ab17550-d5c4-44a7-92d5-79abf016494d\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/02\/9ab17550-d5c4-44a7-92d5-79abf016494d.jpg\" alt=\"9ab17550-d5c4-44a7-92d5-79abf016494d\" width=\"782\" height=\"484\" \/><\/p>\n<p data-vmark=\"155d\">Google shared Magika&#039;s performance data. The benchmark evaluation test results of 1 million files in more than 100 formats showed that Magika&#039;s performance was about 20% higher than existing tools. Magika&#039;s precision and recall rates both reached more than 99%.<\/p>\n<p data-vmark=\"24a0\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-3999\" title=\"3367b6ce-1675-4729-9110-4b15bb550deb\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/02\/3367b6ce-1675-4729-9110-4b15bb550deb.jpg\" alt=\"3367b6ce-1675-4729-9110-4b15bb550deb\" width=\"1600\" height=\"989\" \/><\/p>\n<p data-vmark=\"279a\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-4000\" title=\"0a9268ab-56b5-4bf0-b309-4afdc75a44e5\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/02\/0a9268ab-56b5-4bf0-b309-4afdc75a44e5.jpg\" alt=\"0a9268ab-56b5-4bf0-b309-4afdc75a44e5\" width=\"1600\" height=\"1290\" \/><\/p>\n<p data-vmark=\"4587\">Internally, Google has used Magika to strengthen user security. The system has been deployed at scale to send files in Gmail, Drive, and Safe Browsing to the appropriate security and content policy scanners. Compared with the previous system that relied on manually created rules, Google has found that Magika improves the accuracy of file type identification by 50%.<\/p>\n<p data-vmark=\"1552\">Google said that the integration of Magika with VirusTotal will further improve the efficiency and accuracy of the platform. Magika will act as a pre-filter before VirusTotal&#039;s Code Insight analyzes the file. Code Insight uses Google&#039;s generative artificial intelligence to detect malicious code.<\/p>","protected":false},"excerpt":{"rendered":"<p>Google recently updated a blog post announcing the open-source Magika, which recognizes file formats and content types quickly and efficiently based on artificial intelligence, and the related source code is hosted on GitHub. Magika uses a custom, highly optimized deep learning model to accurately identify file types within milliseconds, even when running on a CPU. Google shares Magika's performance data, with benchmark evaluation tests of 1 million files in more than 100 formats showing that Magika outperforms existing tools by about 20%, and that Magika achieves more than 99% in both precision and recall. Internally, Google has utilized Magika to enhance user security. It has been deployed at scale to integrate Gma<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[1256,219,281],"collection":[],"class_list":["post-3996","post","type-post","status-publish","format-standard","hentry","category-news","tag-magika","tag-219","tag-281"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/3996","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=3996"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/3996\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=3996"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=3996"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=3996"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=3996"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}