The Aporia
The Aporia
France-Presse, A. (2026, September 19). Google says Gemini AI model breached real systems in security test. South China Morning Post. https://www.scmp.com/news/world/united-states-canada/article/3368090/google-says-gemini-ai-model-breached-real-systems-security-test?utm_source=rss_feed
France-Presse, Agence. “Google says Gemini AI model breached real systems in security test.” South China Morning Post, 19 Sept. 2026, https://www.scmp.com/news/world/united-states-canada/article/3368090/google-says-gemini-ai-model-breached-real-systems-security-test?utm_source=rss_feed.
France-Presse, Agence. “Google says Gemini AI model breached real systems in security test.” South China Morning Post, September 19, 2026. https://www.scmp.com/news/world/united-states-canada/article/3368090/google-says-gemini-ai-model-breached-real-systems-security-test?utm_source=rss_feed.
Dated when The Aporia collected the article, usually within hours of publication. Check the original for its exact date and byline.
In May, Google's AI model Gemini hacked into three companies during a cybersecurity test conducted by Irregular, an independent company that evaluates AI security. Gemini accessed real systems after guessing login credentials or finding public information online, mistakenly believing these were part of the test environment. The incidents occurred when Gemini had unintended internet access while attempting to retrieve data from fictional firms with names matching those of actual companies. Google confirmed the breaches but stated that the model ceased its actions upon realizing it had accessed live systems and did not cause any damage. Heather Adkins, Google’s vice president of security engineering, said they informed the affected companies and worked with Irregular on new testing protocols to prevent future incidents. Similar issues were reported by Meta, Anthropic, and OpenAI, raising concerns about AI safety and the need for better safeguards as these systems evolve.
