Google says private companies and researchers are trying to copy Gemini’s capabilities by repeatedly prompting it at scale.
says its flagship artificial intelligence chatbot, Gemini, has been inundated by “commercially motivated” actors who are trying to clone it by repeatedly prompting it, sometimes with thousands of different queries — including one campaign that prompted Gemini more than 100,000 times.
In a report published Thursday, Google said it has increasingly come under “distillation attacks,” or repeated questions designed to get a chatbot to reveal its inner workings. Google described the activity as “model extraction,” in which would-be copycats probe the system for the patterns and logic that make it work. The attackers appear to want to use the information to build or bolster their own AI, it said.The company believes the culprits are mostly private companies or researchers looking to gain a competitive advantage. A spokesperson told NBC News that Google believes the attacks have come from around the world but declined to share additional details about what was known about the suspects. The scope of attacks on Gemini indicates that they most likely are or soon will be common against smaller companies’ custom AI tools, as well, said John Hultquist, the chief analyst of Google’s Threat Intelligence Group. “We’re going to be the canary in the coal mine for far more incidents,” Hultquist said. He declined to name suspects.have spent billions of dollars racing to develop their AI chatbots, or large language models, and consider the inner workings of their top models to be extremely valuable proprietary information.Even though they have mechanisms to try to identify distillation attacks and block the people behind them, major LLMs are inherently vulnerable to distillation because they are open to anyone on the internet. Google has integrated its artificial intelligence platform Gemini into apps such as Maps and Waze to make it easier and more elaborate for users. Scott McGrew reports. Many of the attacks were crafted to tease out the algorithms that help Gemini “reason,” or decide how to process information, Google said. Hultquist said that as more companies design their own custom LLMs trained on potentially sensitive data, they become vulnerable to similar attacks. “Let’s say your LLM has been trained on 100 years of secret thinking of the way you trade. Theoretically, you could distill some of that,” he said.2026 Milan Cortina Olympics
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Google’s 100-year AI gambit: Alphabet taps bond market in a big wayThis is the first time a tech company has tried such an offering since the dotcom frenzy of the late 1990s.
Read more »
First gray wolf enters Los Angeles County in 100 yearsFor the first time in a century, biologists have documented a gray wolf in Los Angeles County over the weekend, a sign that these predators that were eliminated from the state by hunters are making…
Read more »
Panasonic Lumix S 100-500mm f/5-7.1 O.I.S. Review: Slow and SteadyThe Panasonic Lumix S 100-500mm f/5-7.1 lens is not the fastest on the block, but it is compact, portable, and very stable.
Read more »
Bond investors are betting on another 100 years of GoogleBusiness Insider tells the global tech, finance, stock market, media, economy, lifestyle, real estate, AI and innovative stories you want to know.
Read more »
Google pushes AI shopping features in search and Gemini chatbotGoogle is adding a way for consumers to buy things while seeking artificial intelligence-powered answers on search and in its Gemini chatbot, part of a plan to make money more directly from consume…
Read more »
Google: Gemini hit with 100,000+ prompts in cloning attemptKevin Collier is a reporter covering cybersecurity, privacy and technology policy for NBC News.
Read more »