Attackers prompted Gemini over 100,000 times while trying to clone it, Google says

ai, AI (Artificial Intelligence), AI language models, AI security, Artificial Intelligence, Biz & IT, ChatGPT, chatgtp, deepseek, Distillation, Gemini, Google, Google Gemini, Large Language Models, LLMs, Machine Learning, OpenAI

On Thursday, Google announced that “commercially motivated” actors have attempted to clone knowledge from its Gemini AI chatbot by simply prompting it. One adversarial session reportedly prompted the model more than 100,000 times across various non-English languages, collecting responses ostensibly to train a cheaper copycat. Google published the findings in what amounts to a quarterly […]

Attackers prompted Gemini over 100,000 times while trying to clone it, Google says Read More »