{"id":4013,"date":"2026-05-12T17:43:42","date_gmt":"2026-05-12T14:43:42","guid":{"rendered":"https:\/\/newsroomin.eu\/en\/?p=4013"},"modified":"2026-05-26T11:09:25","modified_gmt":"2026-05-26T08:09:25","slug":"google-report-new-ai-exploit-used-in-cyberattacks","status":"publish","type":"post","link":"https:\/\/newsroomin.eu\/en\/google-report-new-ai-exploit-used-in-cyberattacks\/","title":{"rendered":"Google Report: New AI Exploit Used in Cyberattacks"},"content":{"rendered":"\n
\"Digital
Zero Day | Image source: NEWSROOM IN<\/strong><\/a><\/figcaption><\/figure>\n\n\n\n

Google<\/strong> Threat Intelligence Group has published a report<\/a> detailing how a functional AI exploit<\/strong> has transitioned artificial intelligence from a digital assistant to an active participant in cyberattacks. For the first time, researchers recorded an instance where AI developed a functional exploit for mass attacks almost from scratch.<\/p>\n\n\n\n

NEWSROOM IN<\/strong><\/a> examines the severity of this development and whether current security measures<\/a> remain effective.<\/p>\n\n\n\n

AI Exploit Potential: What Has Changed for Bad Actors?<\/h5>\n\n\n\n

Previously, hackers primarily used chatbots to craft convincing phishing emails. Now, state-sponsored groups from China and North Korea, such as the notorious APT45<\/strong>, are utilizing neural networks as “security auditors.”<\/p>\n\n\n\n

    \n
  • Finding Zero-Day Vulnerabilities:<\/strong> These are the most dangerous security flaws that are unknown even to developers. AI has learned to identify not just technical errors, but logical contradictions<\/strong> in code that standard scanners typically miss.<\/li>\n\n\n\n
  • Hallucinations as Evidence:<\/strong> Google experts identified an AI-written exploit by specific markers, including training-related comments in the code, non-existent security ratings, and formatting typical of Python-based AI models.<\/li>\n<\/ul>\n\n\n\n
    The PROMPTSPY Backdoor: Remote Device Control<\/h5>\n\n\n\n

    A significant example of this new era is the Android malware PROMPTSPY<\/strong>. This program uses the Gemini<\/strong> model to analyze a user’s screen by reading the interface structure. It sends this data to the neural network and receives commands on where to click or swipe.<\/p>\n\n\n\n

    PROMPTSPY can independently enter PIN codes, intercept pattern locks, and prevent its own deletion by creating invisible elements over “Uninstall” buttons. Effectively, a “ghost user” controls the device with greater speed and precision than the owner.<\/p>\n\n\n\n

    Noise Tactics: AI-Generated Junk Code<\/h5>\n\n\n\n

    To evade antivirus detection, hackers use AI to create “informational noise.” Programs like CANFAIL<\/strong> and LONGSTREAM<\/strong> are filled with thousands of lines of useless AI-written code. For example, the software may include dozens of daylight savings time checks that perform no function but make the program appear legitimate to security scanners.<\/p>\n\n\n\n

    The Main Question: Is It Time to Worry?<\/h5>\n\n\n\n

    The current verdict remains cautious: the situation is manageable for now, but with certain caveats.<\/p>\n\n\n\n

    Why panic is not yet necessary:<\/strong><\/p>\n\n\n\n

      \n
    • Google is staying ahead:<\/strong> In the recent case, company experts detected the AI exploit before it could be deployed.<\/li>\n\n\n\n
    • Shield against the sword:<\/strong> Google uses the same AI technology to identify and automatically patch vulnerabilities, creating an algorithmic arms race where defensive models are equally powerful.<\/li>\n<\/ul>\n\n\n\n

      Reasons for concern:<\/strong><\/p>\n\n\n\n

        \n
      • Autonomy:<\/strong> Hackers are moving toward systems like Hexstrike<\/strong>, which can conduct reconnaissance and coordinate attacks without human intervention.<\/li>\n\n\n\n
      • Supply chain trust:<\/strong> Attackers have begun targeting popular GitHub libraries, such as LiteLLM<\/strong>, which are used by AI developers worldwide.<\/li>\n<\/ul>\n\n\n\n

        Expert Advice:<\/strong> In the era of AI hackers, standard two-factor authentication (2FA) via SMS is becoming increasingly vulnerable. Users should switch to hardware security keys or authenticator apps. AI can analyze logic, but it cannot bypass a physical key.<\/p>\n","protected":false},"excerpt":{"rendered":"

        Google Threat Intelligence Group has published a report detailing how a functional AI exploit has transitioned artificial intelligence from a digital assistant to an active participant in cyberattacks. For the first time, researchers recorded an instance where AI developed a functional exploit for mass attacks almost from scratch. NEWSROOM IN examines the severity of this [\u2026]<\/p>\n","protected":false},"author":1,"featured_media":4012,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_newsroomin_seo_keywords":"","_newsroomin_seo_lead_override":"","_newsroomin_disable_ads":false,"_newsroomin_is_archived":"","_newsroomin_tooltips":[],"footnotes":""},"categories":[15],"tags":[423,738,1349,1348,53],"class_list":["post-4013","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-futur","tag-ai","tag-cybersecurity","tag-exploit","tag-gemini","tag-google"],"tooltips":[],"newsroomin_tooltips":[],"_links":{"self":[{"href":"https:\/\/newsroomin.eu\/en\/wp-json\/wp\/v2\/posts\/4013","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/newsroomin.eu\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/newsroomin.eu\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/newsroomin.eu\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/newsroomin.eu\/en\/wp-json\/wp\/v2\/comments?post=4013"}],"version-history":[{"count":0,"href":"https:\/\/newsroomin.eu\/en\/wp-json\/wp\/v2\/posts\/4013\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/newsroomin.eu\/en\/wp-json\/wp\/v2\/media\/4012"}],"wp:attachment":[{"href":"https:\/\/newsroomin.eu\/en\/wp-json\/wp\/v2\/media?parent=4013"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/newsroomin.eu\/en\/wp-json\/wp\/v2\/categories?post=4013"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/newsroomin.eu\/en\/wp-json\/wp\/v2\/tags?post=4013"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}