https://www.infoq.com InfoQ Differential Privacy feed https://www.infoq.com/news/2025/09/google-differential-privacy-llm/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Differential+Privacy <img src="https://res.infoq.com/news/2025/09/google-differential-privacy-llm/en/headerimage/gemma-3n-architecture-1758820807365.jpeg"/><p>VaultGemma is a 1B-parameter Gemma 2-based LLM that Google trained from scratch using differential privacy (DP) with the aim of preventing the model from memorizing and later regurgitating training data. While still a research model, VaultGemma could enable applications cases in healthcare, finance, legal, and other regulated sectors.</p> <i>By Sergio De Simone</i> Data Privacy Google Large language models Differential Privacy AI, ML & Data Engineering news Thu, 25 Sep 2025 18:00:00 GMT https://www.infoq.com/news/2025/09/google-differential-privacy-llm/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Differential+Privacy Sergio De Simone 2025-09-25T18:00:00Z /news/2025/09/google-differential-privacy-llm/en