Meta has announced that it will continue with its plan to use millions of publicly available posts from UK Facebook and Instagram users to train its artificial intelligence technology. Although this practice is largely prohibited under EU privacy laws, Meta states that it has been in active communication with the UK Information Commissioner's Office (ICO), after previously pausing similar proposals in June. The pause was due to the ICO's warnings that tech companies must respect user privacy when developing generative AI.

Against the backdrop of tech giants like Google and Microsoft introducing AI features into their email services, Proton Mail, known for its privacy and security, has launched its own AI writing assistant - Proton Scribe. This new feature aims to help users more efficiently compose and optimize emails while strictly protecting user privacy. Proton Scribe has been designed with privacy protection in mind. Since Proton Mail uses zero-access encryption, Scribe cannot access users' inbox data for tra

French startup Nijta focuses on AI-driven voice anonymization technology. Nijta's product, VoiceHarbor, enables voice anonymization while complying with data privacy regulations. The main market for Nijta is in Europe, benefiting from strict GDPR data privacy laws. The company plans to expand into the B2C market, with a focus on protecting voice messages and other related areas.

Patronus AI is a startup based in the United States that focuses on AI model safety and governance. The company has just completed a $3 million Series A funding round led by Lightspeed China. Patronus AI primarily provides AI model security assessment, monitoring, and enhancement platforms for enterprise clients. The company utilizes adversarial generative networks to offer security assessment services for AI models to its clients. Patronus AI stated that this funding round will accelerate product development and expand its R&D team.