mlsanityData to 7 Oct 2026

HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data

arXiv 2011.01805 ↗First posted 3 Nov 2020cs.CR cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Privacy-preserving solutions enable companies to offload confidential data to third-party services while fulfilling their government regulations. To accomplish this, they leverage various cryptographic techniques such as Homomorphic Encryption (HE), which allows performing computation on encrypted data. Most HE schemes work in a SIMD fashion, and the data packing method can dramatically affect the running time and memory costs. Finding a packing method that leads to an optimal performant implementation is a hard task. We present a simple and intuitive framework that abstracts the packing decision for the user. We explain its underlying data structures and optimizer, and propose a novel algorithm for performing 2D convolution operations. We used this framework to implement an HE-friendly version of AlexNet, which runs in three minutes, several orders of magnitude faster than other state-of-the-art solutions that only use HE.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 8; 2024: 1; 2025: 4; 2026: 6.

22 papers.

Sort:

By area:

  1. 2023FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning Systemcited by 38
  2. 2023Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryptioncited by 19
  3. 2021A methodology for training homomorphicencryption friendly neural networkscited by 10
  4. 2023HyPHEN: A Hybrid Packing Method and Optimizations for Homomorphic Encryption-Based Neural Networkscited by 9
  5. 2024Power-Softmax: Towards Secure LLM Inference over Encrypted Datacited by 6
  6. 2023Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryptioncited by 5
  7. 2022Efficient Pruning for Machine Learning Under Homomorphic Encryptioncited by 2
  8. 2025Efficient Decoding Methods for Language Models on Encrypted Datacited by 2
  9. 2026AEGIS: Scaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism on Multi-GPU Systemscited by 2
  10. 2023HE-MAN -- Homomorphically Encrypted MAchine learning with oNnx modelscited by 1
  11. 2023Efficient Skip Connections Realization for Secure Inference on Encrypted Datacited by 1
  12. 2025A Framework for Double-Blind Federated Adaptation of Foundation Modelscited by 1
10 more
  1. 2022mPSAuth: Privacy-Preserving and Scalable Authentication for Mobile Web Applicationscited by 0
  2. 2023High-Resolution Convolutional Neural Networks on Homomorphically Encrypted Data via Sharding Ciphertextscited by 0
  3. 2023MetisFL: An Embarrassingly Parallelized Controller for Scalable & Efficient Federated Learning Workflowscited by 0
  4. 2025DESIGN: Encrypted GNN Inference via Server-Side Input Graph Pruningcited by 0
  5. 2025FHE-Agent: Automating CKKS Configuration for Practical Encrypted Inference via an LLM-Guided Agentic Frameworkcited by 0
  6. 2026PADER: Paillier-based Secure Decentralized Social Recommendationcited by 0
  7. 2026FEnc2: Unifying Data Packing for Efficient Private Inference via Convolution and Architecture-Aware Fragment Encodingcited by 0
  8. 2026Detecting and Understanding Vulnerabilities in Fully Homomorphic Encryption Frameworkscited by 0
  9. 2026OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-designcited by 0
  10. 2026Fiona: Accelerating FHE Inference with Packing-Aware Ternary Weightscited by 0