New AI Training Method Keeps Smart Devices Private and Reliable
Your phone's AI could get smarter without sharing your data—and resist bad info.
Deep Dive
The current browse context is References & Citations. arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on arXiv's website.
Both individuals and organizations that work with arXivLabs have embraced and accepted arXiv's values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. If you have an idea for a project that will add value for arXiv's community, you can learn more about arXivLabs.
Key Points
- Federated learning lets AI learn from many devices without sharing your private data.
- New method makes AI robust against bad or malicious data from some devices.
- This could lead to smarter, safer AI on your phone and smart home gadgets.
Why It Matters
Your devices could get smarter AI without sacrificing privacy or falling for hackers' tricks.