Metraipolis › archive › dc_ff192dff9317

EHEIR: Efficient Homomorphic Encrypted Inference via Architectural Redesign (2026) · DOI 10.1145/3843768

Source
Metraipolis archive
Original
https://doi.org/10.1145/3843768
License (as archived)
CC-BY-4.0
Archived
2026-10-08T01:15:21.442Z
SHA-256 of the archived text
3d0427783b29cbe5ca5118aa8e7cb5aff0e6c5a26d32d8d6b9a1bc15607375af
Stable URL of this page
https://metraipolis.com/documento/dc_ff192dff9317

How to cite

EHEIR: Efficient Homomorphic Encrypted Inference via Architectural Redesign (2026) · DOI 10.1145/3843768 — Metraipolis archive, https://doi.org/10.1145/3843768 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_ff192dff9317 (Metraipolis archive dc_ff192dff9317, sha256 3d0427783b29cbe5ca5118aa8e7cb5aff0e6c5a26d32d8d6b9a1bc15607375af)
BibTeX
@misc{dcff192dff9317,
  title = {EHEIR: Efficient Homomorphic Encrypted Inference via Architectural Redesign (2026) · DOI 10.1145/3843768},
  howpublished = {Metraipolis archive},
  url = {https://doi.org/10.1145/3843768},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_ff192dff9317; sha256 3d0427783b29cbe5ca5118aa8e7cb5aff0e6c5a26d32d8d6b9a1bc15607375af},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://doi.org/10.1145/3843768. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Articolo recente con licenza aperta: scheda dai metadati Crossref (journal-article).
Titolo: EHEIR: Efficient Homomorphic Encrypted Inference via Architectural Redesign
Autori: Reeshav Chowdhury, Anoop Mishra, Deepak Khazanchi, Ayantika Chatterjee
Pubblicato: 2026-09-23 · in: ACM Transactions on Internet Technology · editore: Association for Computing Machinery (ACM)
DOI: https://doi.org/10.1145/3843768
Licenza dell'articolo: CC-BY-4.0

Abstract (testo degli autori, CC-BY-4.0):
Encrypted inference under homomorphic encryption (HE) imposes stringent constraints on computation, making the direct deployment of deep neural networks infeasible on resource-constrained edge devices. Existing approaches, such as FHEEDGE and UniHENN, primarily focus on improving the efficiency of encrypted computation through algorithmic and systems-level optimizations. In contrast, we adopt a complementary perspective by redesigning neural architectures to align with the inherent cost model of HE operations. In this work, we present a framework that reformulates HE-aware model design as a constrained neural architecture search problem, where the objective is to identify architectures that are both cryptographically feasible and computationally efficient while preserving task performance. Starting from a pretrained network, we perform a structured, iterative transformation process that includes HE-compatible operator substitutions, depth–width tradeoffs, and rotation-efficient design strategies such as successive average pooling. These transformations are guided by constraints on ciphertext slots, multiplicative depth, and rotation complexity, and are evaluated using short-horizon training to efficiently explore the architecture space. We provide a theoretical analysis showing that the transformed network approximates the original model with bounded error under layer-wise Lipschitz propagation, ensuring controlled performance degradation. As a case study, we apply the proposed framework to encrypted crack detection for structural health monitoring. The optimized model achieves an execution time of 86.5 seconds for single-threaded CPU inference in the encrypted domain, compared with an estimated 3.5 hours required by the original encrypted convolutional pipeline. Furthermore, deployment on a Raspberry Pi demonstrates end-to-end encrypted inference within approximately 7.5 minutes. These results highlight that architecture-level optimization, when framed as a constrained search problem, complements existing algorithmic acceleration approaches and provides a practical pathway for enabling efficient and privacy-preserving inference on edge devices across a broad class of sensitive AI workloads.

Fonte: https://api.crossref.org/works/10.1145%2F3843768 — metadati Crossref, consultati il 2026-10-07. Interrogazione: «efficient inference quantization».