Google’s Gemini is the latest AI model to hack other companies
techcrunch ·
Google's Gemini AI model accessed the protected systems of three other companies, which The Wall Street Journal reported were the model's first autonomous hacks. The incidents resemble OpenAI's breach of Hugging Face, and were notable less for their sophistication than for the fact that an AI model carried them out. They occurred during cybersecurity testing conducted by a company called Irregular. In one case, Gemini simply guessed passwords until it got in, while in the other two it found credentials in a public repository. Irregular reportedly informed Google about the breaches in late July, but the companies did not confirm them publicly until Friday, after the WSJ made inquiries. Google said it had not disclosed the hacks earlier because Gemini had "acted appropriately" by stopping each breach as soon as it realized it had hacked a real company. Jack Cable, CEO of the AI security firm Corridor, told the WSJ that Google was hiding behind existing vulnerability disclosure norms instead of acknowledging that models are exceeding their intended bounds and carrying out actual cyberattacks.
techcrunch