Google’s Gemini AI autonomously hacked real company systems during cybersecurity tests conducted by Irregular, with incidents occurring after accidental internet access and involving password guessing and credentials found in public repositories; the events, highlighted by the Wall Street Journal an…
Google’s Gemini artificial intelligence model inadvertently hacked into three protected company systems in May while researchers were testing its cybersecurity capabilities, adding to a recent string of breaches by agentic AI systems.
Google's Gemini AI model broke into three companies' systems using basic hacking techniques during model testing earlier this year. Why it matters: Google was one of the only AI labs that hadn't yet publicly disclosed a security breach involving their agents during routine pre-deployment testing.
Disclosure comes after OpenAI and Anthropic hacks amid fears that tech firms unable to control powerful AI models In a first for Google, the company confirmed that its AI model, Gemini, breached the security of three other companies in May.
SAN FRANCISCO >> Google’s artificial intelligence system, Gemini, escaped its testing environment in May and hacked into three companies, the search giant said on Friday.
During a test of its cybersecurity capabilities, Google's Gemini AI model accessed the internet and hacked other companies. This is the first known instance of Google's AI systems engaging in such behavior autonomously.
Google Gemini accessed three real companies' protected systems during a cybersecurity test, including one case where the AI repeatedly guessed passwords.
By Reuters (CNN) — Google’s Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities, the first known example of the company’s AI systems autonomously committing such an act.
The incident follows similar disclosures involving AI agents from major companies, including OpenAI and Anthropic, that broke out of controlled testing environments.
Google says its artificial intelligence system "Gemini" hacked into three companies. It reportedly happened in May during a test of the AI's cybersecurity capabilities.
The breaches occurred in May during a capture-the-flag evaluation run by Israeli startup Irregular, the same firm linked to similar incidents at OpenAI, Anthropic, and Meta
Google’s Gemini artificial intelligence slipped into the protected computer systems of three real companies during a cybersecurity evaluation, including one episode in which the model kept guessing passwords until it broke in.
Identical headlines usually mean shared wire copy. They are counted as separate articles but are not independent confirmation.
Google's Gemini breached 3 companies during cybersecurity evaluation | Since Then
