Paper 2024/1099

FHE-MENNs: Opportunities and Pitfalls for Accelerating Fully Homomorphic Private Inference with Multi-Exit Neural Networks

Lars Wolfgang Folkerts, University of Delaware
Nektarios Georgios Tsoutsos, University of Delaware
Abstract

With concerns about data privacy growing in a connected world, cryptography researchers have focused on fully homomorphic encryption (FHE) for promising machine learning as a service solutions. Recent advancements have lowered the computational cost by several orders of magnitude, but the latency of fully homomorphic neural networks remains a barrier to adoption. This work proposes using multi-exit neural networks (MENNs) to accelerate the FHE inference. MENNs are network architectures that provide several exit points along the depth of the network. This approach allows users to employ results from any exit and terminate the computation early, saving both time and power. First, this work weighs the latency, communication, accuracy, and computational resource benefits of running FHE-based MENN inference. Then, we present the TorMENNt attack that can exploit the user's early termination decision to launch a concrete side-channel on MENNs. We demonstrate that the TorMENNt attack can predict the private image classification output of an image set for both FHE and plaintext threat models. We discuss possible countermeasures to mitigate the attack and examine their effectiveness. Finally, we tie the privacy risks with a cost-benefit analysis to obtain a practical roadmap for FHE-based MENN adoption.

Metadata
Available format(s)
PDF
Category
Applications
Publication info
Preprint.
Keywords
Fully Homomorphic EncryptionMulti-Exit Neural NetworksPrivacy Preserving Machine Learning
Contact author(s)
folkerts @ udel edu
tsoutsos @ udel edu
History
2024-07-08: approved
2024-07-05: received
See all versions
Short URL
https://ia.cr/2024/1099
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2024/1099,
      author = {Lars Wolfgang Folkerts and Nektarios Georgios Tsoutsos},
      title = {{FHE}-{MENNs}: Opportunities and Pitfalls for Accelerating Fully Homomorphic Private Inference with Multi-Exit Neural Networks},
      howpublished = {Cryptology {ePrint} Archive, Paper 2024/1099},
      year = {2024},
      url = {https://eprint.iacr.org/2024/1099}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.