Google Research AI blog

MARCH 2, 2023

While offering substantial additional protections, a fully malicious server might still be able to get around the DDP guarantees either by manipulating the public key exchange of SecAgg or by injecting a sufficient number of "fake" malicious clients that don’t add the prescribed noise into the aggregation pool.

ML 119

ML ML Machine Learning Machine Learning 119

Google Research AI blog

MARCH 6, 2023

Learn More Check out our paper here. Researchers can request access to the USM API here.

Supervised Learning 140

Supervised Learning AI AI Algorithm 140

AWS Machine Learning Blog

AUGUST 16, 2023

This is a guest blog post co-written with Ben Veasey, Jeremy Anderson, Jordan Knight, and June Li from Travelers. June Li is a data scientist at Travelers’s Business Insurance’s Artificial Intelligence team, where she leads and coordinates work in the AI imagery portfolio. Andrew Ang is a Sr.

ML 71

ML ML AWS Data Scientist 71

Google Research AI blog

MAY 4, 2023

Acknowledgements The work described is co-authored by: Weicheng Kuo, AJ Piergiovanni, Dahun Kim, Xiyang Luo, Ben Caine, Wei Li, Abhijit Ogale, Luowei Zhou, Andrew Dai, Zhifeng Chen, Claire Cui, and Anelia Angelova.

81

81