Edgar Cervantes / Android Authority
TL;DR Google report claims one campaign sent over 100,000 prompts to Gemini in an attempt to clone the model.
Attackers tried to coax Gemini into revealing more details about its internal reasoning abilities.
Google says it detected the behavior, blocked associated accounts, and strengthened safeguards against misuse.
Copying a successful product has been a practice as long as tools and technologies have existed, but chatbots are a special case. Competitors can’t pull them apart, but they can ask the AI as many questions as you like in an attempt to figure out how it works. According to a new report from Google, that’s exactly how some actors have been trying to clone Gemini. In one case, Google says a single campaign sent more than 100,000 prompts to the chatbot, in what it describes as a large-scale model-extraction attempt.
The findings come from Google’s latest Threat Intelligence Group report (via NBC News), which outlines a rise in so-called “distillation” attacks. In simple terms, that means repeatedly querying a model to study how it responds, then using those answers to train a competing system. Google says this activity violates its terms of service and amounts to intellectual property theft, even though the attackers are using legitimate API access rather than breaking into its systems.
Don’t want to miss the best from Android Authority? Set us as a favorite source in Google Discover to never miss our latest exclusive reports, expert analysis, and much more.
to never miss our latest exclusive reports, expert analysis, and much more. You can also set us as a preferred source in Google Search by clicking the button below.
One campaign highlighted in the report specifically targeted Gemini’s reasoning capabilities. While Gemini doesn’t normally expose its full internal “chain of thought,” Google says attackers tried to coerce it into revealing more detailed reasoning abilities. The scale of the prompts — over 100,000 in this case — suggests an effort to replicate Gemini’s ability to reason across different tasks and even in non-English languages. Google says its systems detected the activity in real time and adjusted protections to prevent internal reasoning details from being exposed.
What feature should Gemini copy from ChatGPT first? 333 votes Better long-term memory 52 % Folder organization 19 % Third-party integrations 17 % Cleaner interface 12 %
... continue reading