REVIEW 3 cited by
Does Fully Homomorphic Encryption Need Compute Acceleration?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Fully Homomorphic Encryption (FHE) allows arbitrarily complex computations on encrypted data without ever needing to decrypt it, thus enabling us to maintain data privacy on third-party systems. Unfortunately, sustaining deep computations with FHE requires a periodic noise reduction step known as bootstrapping. The cost of the bootstrapping operation is one of the primary barriers to the wide-spread adoption of FHE. In this paper, we present an in-depth architectural analysis of the bootstrapping step in FHE. First, we observe that secure implementations of bootstrapping exhibit a low arithmetic intensity (<1 Op/byte), require large caches (>100 MB), and are heavily bound by the main memory bandwidth. Consequently, we demonstrate that existing workloads observe marginal performance gains from the design of bespoke high-throughput arithmetic units tailored to FHE. Second, we propose several cache-friendly algorithmic optimizations that improve the throughput in FHE bootstrapping by enabling up to 3.2x higher arithmetic intensity and 4.6x lower memory bandwidth. Our optimizations apply to a wide range of structurally similar computations such as private evaluation and training of machine learning models. Finally, we incorporate these optimizations into an architectural tool which, given a cache size, memory subsystem, the number of functional units and a desired security level, selects optimal cryptosystem parameters to maximize the bootstrapping throughput. Our optimized bootstrapping implementation represents a best-case scenario for compute acceleration of FHE. We show that despite these optimizations, bootstrapping continues to be bottlenecked by main memory bandwidth. We propose new research directions to address the underlying memory bottleneck. In summary, our answer to the titular question is: yes, but only after addressing the memory bottleneck!
Forward citations
Cited by 3 Pith papers
-
FIDESlib: A Fully-Fledged Open-Source FHE Library for Efficient CKKS on GPUs
FIDESlib is a fully open-source CKKS GPU library with all primitives including bootstrapping, reporting over 70x bootstrapping speedup over optimized OpenFHE and better performance than Phantom for shared operations.
-
Leveraging Photonic Interconnects for Scalable and Efficient Fully Homomorphic Encryption
A proposed optical interconnect for FHE accelerators claims 1.6 TB/s through 128 channels, while the supporting simulation only reaches 10 Gb/s per wavelength.
-
Secure Distributed Learning for CAVs: Defending Against Gradient Leakage with Leveled Homomorphic Encryption
The paper claims CKKS-based selective encryption can protect federated learning from gradient leakage while preserving accuracy, but it never runs a leakage attack and gives the server the decryption key.
Discussion (0). Continue with ORCID to comment.