Privacy Breach Risk in Nvidia AI Technology Raises Concern Among Researchers

Researchers have raised concerns over privacy breaches in Nvidia’s artificial intelligence (AI) software, after finding that the NeMo Framework is susceptible to manipulation that puts private data at risk. Large language models, which power generative AI products like chatbots, are among the products affected. However, after using the Nvidia system on their own data sets, the analysts said it was easy to bypass restrictions and trap the AI technology into releasing personally identifiable information. In response, the researchers have advised their customers to avoid the Nvidia software. The tech firm has informed Robust Intelligence that it has fixed one of the root causes behind the problem.