Boosting Secure AI: HAWK Accelerator and FHEFusion Compiler Break New Ground

This article highlights two cutting‑edge works from Ant Group’s research team—HAWK, a fixed‑word key decomposition switching accelerator that overcomes hardware challenges for FHE, and FHEFusion, a compiler framework that introduces operator fusion to dramatically speed CKKS‑based DNN inference—showcasing their designs, optimizations, and experimental gains.

Compiler OptimizationDNN inferenceFully Homomorphic Encryption

0 likes · 7 min read

Boosting Secure AI: HAWK Accelerator and FHEFusion Compiler Break New Ground

AntTech

Aug 16, 2023 · Information Security

Ant Group Research Institute Presents Two First-Author Papers at USENIX Security 2023 on Secure MPC for GBDT Training and Efficient 3PC for Binary Circuits

At the 32nd USENIX Security Symposium in Anaheim, Ant Group’s Research Institute sponsored the event and showcased two first‑author papers—one introducing the Squirrel framework for fast, secure two‑party computation of Gradient Boosting Decision Trees, and another proposing an efficient 3‑party protocol for binary circuits in maliciously‑secure DNN inference.

DNN inferenceMPCUSENIX Security

0 likes · 3 min read

Ant Group Research Institute Presents Two First-Author Papers at USENIX Security 2023 on Secure MPC for GBDT Training and Efficient 3PC for Binary Circuits

Network Intelligence Research Center (NIRC)

Jun 27, 2023 · Artificial Intelligence

Microsecond-Scale GPU Preemption Enables Concurrent Real-Time DNN Inference

REEF introduces a reset‑based preemption mechanism and dynamic kernel padding to achieve microsecond‑scale GPU kernel preemption, enabling concurrent real‑time and best‑effort DNN inference with only 2 % added latency for real‑time tasks while boosting overall throughput by up to 7.7×, as demonstrated on the DISB benchmark.

DNN inferenceGPU schedulingREEF

0 likes · 9 min read

Microsecond-Scale GPU Preemption Enables Concurrent Real-Time DNN Inference