pllmR22: BumbleBee: Secure Two-party Inference Framework for Large Transformers
BumbleBee implements secure two-party transformer inference with specialized nonlinear protocols and an Apache-2.0 artifact. PLLM status: tracked.
Status: tracked
Year: 2025
Authors: Wen-jie Lu, Zhicong Huang, Zhen Gu, Jingyu Li, Jian Liu, Cheng Hong, Kui Ren, Tao Wei, Wenguang Chen
External source: BumbleBee: Secure Two-party Inference Framework for Large Transformers
Source contribution
BumbleBee implements secure two-party transformer inference with specialized nonlinear protocols and an Apache-2.0 artifact.
PLLM perspective
Reproduce the source workload, then isolate normalization, softmax, activation and communication components for comparison with PLLM plans.
No PLLM BumbleBee reproduction has been executed.
This paper remains tracked. Named modules below are implementation targets, not finished PLLM components; no reproduction, integration, assurance, or matched benchmark is claimed.
The source's boundary remains binding: Both parties are online and hold additive shares; this cannot enter the one-evaluator profile without changing the trust topology.
PLLM modules and documentation
Target module identifiers: protocol.bumblebee, gate.bumblebee_nonlinear, runtime.bumblebee. These identifiers describe scoped work unless this page explicitly links an implementation source. Dependencies: None.
Backlog
This source is assigned to reimplementation priority 8, Full-system comparison targets. Its source-registry order is 22. Follow current gates and unfinished work in the research backlog.
R21: NEXUS: Secure Transformer Inference Made Non-interactive
NEXUS combines approximate HE with lightweight garbled circuits for non-interactive two-party transformer forward inference. PLLM status: tracked.
R23: MPCache: MPC-Friendly KV Cache Eviction for Efficient Private Large Language Model Inference
MPCache evaluates MPC-friendly static and dynamic KV-cache eviction in a three-party SecretFlow/SPU setting; its artifact focuses state selection and operator costs. PLLM status: PLLM reimplementation.