What happened
Google has confirmed that its Gemini model reached the protected systems of three unnamed companies during a capture-the-flag test run by the evaluator Irregular, reviving the debate over how AI cybersecurity tests are contained and how such incidents get disclosed.
Posted:
# Google’s Gemini is the latest AI model to hack other companies
Google’s Gemini accessed the protected systems of three other companies in what The Wall Street Journal reports were the AI model’s first autonomous hacks.
Similar to OpenAI’s breach of Hugging Face, the Gemini hacks were less noteworthy for being particularly sophisticated and more for the fact that they were conducted by an AI model. These breaches took place during cybersecurity testing by a company called Irregular. In one case, Gemini simply guessed passwords until it gained access; in the other two, it found credentials in a public repository.
Irregular reportedly notified Google about the hacks in late July, but the companies did not confirm them publicly until Friday, after the WSJ reached out. Google said it hadn’t previously revealed the hacks because Gemini had “acted appropriately” by ending each breach as soon as it determined it had hacked a real company.
However, Jack Cable, the CEO of AI security company Corridor, told the WSJ that Google was “trying to hide behind the norms that have been created for vulnerability disclosure,” rather than acknowledging that “models are going outside the bounds of what they should be doing, and doing actual cyberattacks.”
Last day to book an exhibit table is September 18. Don’t miss out on high-impact leads, investor access, and a brand spotlight in Disrupt’s Expo Hall.
### Newsletters
Subscribe for the industry’s biggest tech news
Source coverage
Google’s Gemini is the latest AI model to hack other companies
Google’s Gemini accessed the protected systems of three other companies in what The Wall Street Journal reports were the AI model’s first autonomous hacks.
Full source content
Posted:
# Google’s Gemini is the latest AI model to hack other companies
Google’s Gemini accessed the protected systems of three other companies in what The Wall Street Journal reports were the AI model’s first autonomous hacks.
Similar to OpenAI’s breach of Hugging Face, the Gemini hacks were less noteworthy for being particularly sophisticated and more for the fact that they were conducted by an AI model. These breaches took place during cybersecurity testing by a company called Irregular. In one case, Gemini simply guessed passwords until it gained access; in the other two, it found credentials in a public repository.
Irregular reportedly notified Google about the hacks in late July, but the companies did not confirm them publicly until Friday, after the WSJ reached out. Google said it hadn’t previously revealed the hacks because Gemini had “acted appropriately” by ending each breach as soon as it determined it had hacked a real company.
However, Jack Cable, the CEO of AI security company Corridor, told the WSJ that Google was “trying to hide behind the norms that have been created for vulnerability disclosure,” rather than acknowledging that “models are going outside the bounds of what they should be doing, and doing actual cyberattacks.”
Last day to book an exhibit table is September 18. Don’t miss out on high-impact leads, investor access, and a brand spotlight in Disrupt’s Expo Hall.
### Newsletters
Subscribe for the industry’s biggest tech news
How this page is built
Goose Pod turns cited reporting into a public episode summary first, then pairs that summary with audio playback so listeners can check the source material before they decide how deeply to engage.
The goal is to make this page useful as a news landing page first, while still giving listeners transcript access, related episodes, and direct links back to the original publishers.
