July 17, 2024 09:49
Abstract
Title: BumbleBee: Secure Two-party Inference Framework for Large Transformers
Abstract: We introduce BumbleBee, a two-party private inference system designed for efficiency and speed. Key contributions include optimized matrix multiplication protocols reducing communication costs by 80-90%, new protocols for non-linear activation functions improving speed and reducing costs by 80-95%. BumbleBee outperforms previous systems, Iron and BOLT, by a significant margin in both speed and communication efficiency.
More Information
| Date | July 24, 2024 (Wed) 14:30 - 15:30 |
| URL | https://c5dc59ed978213830355fc8978.doorkeeper.jp/events/175673 |
Related Laboratories
last updated on April 9, 2026 15:00Laboratory
![[AIP AI4S Seminar Series #2]Talk by Masaaki Imaizumi<br>(University of Tokyo and RIKEN AIP)-20260318thumbnails](https://aip.riken.jp/wp-content/themes/aipdesign/images/loading.gif)
