Katarzyna Petru
Google has published a new security report detailing the rising attempts to copy advanced artificial intelligence models. The targets of the attacks include Gemini, the company's flagship AI model. According to the document, attackers used over 100,000 queries to analyse and replicate the workings of the system. Google claims these actions fall within a broader wave of attempts to steal intellectual property related to AI. The attacks reportedly originate from countries such as North Korea, Russia, and China. However, the company highlights that the threat primarily concerns model creators, not ordinary users.
What is "model extraction"?
Google defines these activities as so-called extraction attacks, which are systematic examinations of models using legal access. In practice, this means mass generation of queries to understand the workings of AI and using that knowledge to create a competitive system. Such operations can lead to the creation of models in other languages or to replicating functionality without access to the original training data.
Arms Race in the AI World
Experts from Google Threat Intelligence Group warn that the company may just be the first example of a larger problem. In recent years, competition in the AI sector has significantly accelerated, and tensions between tech companies are growing. New, advanced models from Asian companies have entered the market, increasingly competing with leaders from the USA. In the background, disputes are also unfolding over the use of others' technology to train one's own systems.
The Google report shows that with the development of artificial intelligence, the risk of technology theft is also increasing. Attacks involving the mass analysis of models could become one of the main threats to companies developing AI. For users, this means one thing – the race for dominance in the world of AI is just getting started.
source: cnet.com
