{"id":5063,"date":"2025-09-26T09:50:51","date_gmt":"2025-09-26T09:50:51","guid":{"rendered":"https:\/\/cybersecurityinfocus.com\/?p=5063"},"modified":"2025-09-26T09:50:51","modified_gmt":"2025-09-26T09:50:51","slug":"genai-infrastruktur-anfallig-fur-cyberattacken","status":"publish","type":"post","link":"https:\/\/cybersecurityinfocus.com\/?p=5063","title":{"rendered":"GenAI-Infrastruktur anf\u00e4llig f\u00fcr Cyberattacken"},"content":{"rendered":"
\n
\n
\n
\n
<\/div>\n
srcset=”https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?quality=50&strip=all 6000w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=300%2C168&quality=50&strip=all 300w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=768%2C432&quality=50&strip=all 768w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=1024%2C576&quality=50&strip=all 1024w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=1536%2C864&quality=50&strip=all 1536w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=2048%2C1152&quality=50&strip=all 2048w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=1240%2C697&quality=50&strip=all 1240w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=150%2C84&quality=50&strip=all 150w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=854%2C480&quality=50&strip=all 854w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=640%2C360&quality=50&strip=all 640w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=444%2C250&quality=50&strip=all 444w” width=”1024″ height=”576″ sizes=”auto, (max-width: 1024px) 100vw, 1024px”>Chatbot-Assistenten in Unternehmen sind besonders verwundbar, da sie durch Prompt-Injection-Angriffe manipuliert werden k\u00f6nnen.\n

UnImages \u2013 shutterstock.com<\/p>\n<\/div>\n

In einer Umfrage der Marktanalysten von Gartner berichten 29 Prozent der Cybersicherheitsverantwortlichen, dass die in ihrer Organisation verwendeten generativen KI<\/a>-Anwendungen in den vergangenen zw\u00f6lf Monaten Ziel eines Cyberangriffs war.<\/p>\n

Bei 32 Prozent der Unternehmen wurden gezielt Schwachstellen in der Prompt-Struktur ausgenutzt. \u201eInsbesondere Chatbot-Assistenten gelten hier als verwundbar, da sie durch feindselige Prompting-Techniken manipuliert werden k\u00f6nnen \u2013 etwa indem Angreifer Eingaben so gestalten, dass gro\u00dfe Sprachmodelle (LLMs) oder multimodale Modelle voreingenommene oder sogar sch\u00e4dliche Antworten erzeugen\u201c, erkl\u00e4ren die Gartner-Analysten.<\/p>\n

Zudem gaben 62 Prozent der Unternehmen zu, dass sie bereits Opfer von Deepfake-Attacken<\/a> waren \u2013 meist in Kombination mit Social Engineering<\/a> oder automatisierten Angriffstechniken.<\/p>\n

Schutzma\u00dfnahmen erforderlich<\/strong><\/h2>\n

W\u00e4hrend 67 Prozent der befragten Sicherheitsentscheider der Meinung sind, dass diese neuen Risiken umfassende Ver\u00e4nderungen ihrer Cybersecurity-Strategien erfordern, empfiehlt Gartner ein differenzierteres Vorgehen.<\/p>\n

\u201eAnstatt radikale Umbauten oder isolierte Investitionen vorzunehmen, sollten Unternehmen ihre Kernkontrollen konsequent st\u00e4rken und f\u00fcr jede neue Risikokategorie gezielt Ma\u00dfnahmen ergreifen\u201c, r\u00e4t Akif Khan VP Analyst bei Gartner.<\/p>\n

Die Befragung fand zwischen M\u00e4rz und Mai 2025 statt. Sie umfasste 302 Sicherheitsleiter aus Nordamerika, der EMEA- sowie der Asien-Pazifik-Region.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"

srcset=”https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?quality=50&strip=all 6000w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=300%2C168&quality=50&strip=all 300w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=768%2C432&quality=50&strip=all 768w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=1024%2C576&quality=50&strip=all 1024w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=1536%2C864&quality=50&strip=all 1536w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=2048%2C1152&quality=50&strip=all 2048w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=1240%2C697&quality=50&strip=all 1240w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=150%2C84&quality=50&strip=all 150w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=854%2C480&quality=50&strip=all 854w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=640%2C360&quality=50&strip=all 640w, https:\/\/b2b-contenthub.com\/wp-content\/uploads\/2025\/09\/shutterstock_2668474647.jpg?resize=444%2C250&quality=50&strip=all 444w” width=”1024″ height=”576″ sizes=”auto, (max-width: 1024px) 100vw, 1024px”>Chatbot-Assistenten in Unternehmen sind besonders verwundbar, da sie durch Prompt-Injection-Angriffe manipuliert werden k\u00f6nnen. UnImages \u2013 shutterstock.com In einer Umfrage der Marktanalysten von Gartner berichten 29 Prozent der […]<\/p>\n","protected":false},"author":0,"featured_media":5064,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[],"class_list":["post-5063","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-education"],"_links":{"self":[{"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=\/wp\/v2\/posts\/5063"}],"collection":[{"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=5063"}],"version-history":[{"count":0,"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=\/wp\/v2\/posts\/5063\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=\/wp\/v2\/media\/5064"}],"wp:attachment":[{"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5063"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5063"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5063"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}