CryptoUNets: Applying Convolutional Networks to Encrypted Data for Biomedical Image Segmentation

• URL: http://arxiv.org/abs/2504.21543v1
• Date: Wed, 30 Apr 2025 11:37:22 GMT
• Title: CryptoUNets: Applying Convolutional Networks to Encrypted Data for Biomedical Image Segmentation
• Authors: John Chiang,
• Abstract summary: We demonstrate the feasibility of a privacy-preserving U-Net deep learning inference framework, namely, homomorphic encryption-based U-Net inference.<n>To our knowledge, this is the first work to achieve support perform implement enable U-Net inference entirely based on homomorphic encryption.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this manuscript, we demonstrate the feasibility of a privacy-preserving U-Net deep learning inference framework, namely, homomorphic encryption-based U-Net inference. That is, U-Net inference can be performed solely using homomorphic encryption techniques. To our knowledge, this is the first work to achieve support perform implement enable U-Net inference entirely based on homomorphic encryption ?. The primary technical challenge lies in data encoding. To address this, we employ a flexible encoding scheme, termed Double Volley Revolver, which enables effective support for skip connections and upsampling operations within the U-Net architecture. We adopt a tailored HE-friendly U-Net design incorporating square activation functions, mean pooling layers, and transposed convolution layers (implemented as ConvTranspose2d in PyTorch) with a kernel size of 2 and stride of 2. After training the model in plaintext, we deploy the resulting parameters using the HEAAN homomorphic encryption library to perform encrypted U-Net inference.

Related papers

• Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Deep Learning (Inference++) [0.0]
  Homomorphic encryption has emerged as a promising approach for enabling secure machine learning in untrusted environments.<n>In this paper, we propose an improved encoding and computation framework that removes the requirement that a single encrypted ciphertext must fully contain one input image.<n>Our method reformulates the data layout and homomorphic operations to partition high-resolution inputs across multiple ciphertexts.
  arXiv  Detail & Related papers  (2025-12-21T08:40:31Z)
• Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference [0.30586855806896035]
  This work presents a comparative evaluation of Fully Homomorphic Encryption (FHE) and Garbled Circuits (GC) for secure neural network inference.<n>A two-layer neural network (NN) was implemented using the CKKS scheme from the Microsoft SEAL library (FHE) and the TinyGarble2.0 framework (GC) by IntelLabs.<n>Results reveal a trade-off: modular GC offers faster execution and lower memory consumption, while FHE supports non-interactive inference.
  arXiv  Detail & Related papers  (2025-10-08T19:03:40Z)
• Secure Semantic Communication With Homomorphic Encryption [52.5344514499035]
  This paper explores the feasibility of applying homomorphic encryption to SemCom.<n>We propose a task-oriented SemCom scheme secured through homomorphic encryption.
  arXiv  Detail & Related papers  (2025-01-17T13:26:14Z)
• Encryption-Friendly LLM Architecture [11.386436468650016]
  Homomorphic encryption (HE) is a cryptographic protocol supporting arithmetic computations in encrypted states.<n>We propose a modified HE-friendly transformer architecture with an emphasis on inference following personalized (private) fine-tuning.
  arXiv  Detail & Related papers  (2024-10-03T13:48:35Z)
• Privacy preserving layer partitioning for Deep Neural Network models [0.21470800327528838]
  Trusted Execution Environments (TEEs) can introduce significant performance overhead due to additional layers of encryption, decryption, security and integrity checks. We introduce layer partitioning technique and offloading computations to GPU. We conduct experiments to demonstrate the effectiveness of our approach in protecting against input reconstruction attacks developed using trained conditional Generative Adversarial Network(c-GAN)
  arXiv  Detail & Related papers  (2024-04-11T02:39:48Z)
• Towards Diverse Binary Segmentation via A Simple yet General Gated Network [71.19503376629083]
  We propose a simple yet general gated network (GateNet) to tackle binary segmentation tasks. With the help of multi-level gate units, the valuable context information from the encoder can be selectively transmitted to the decoder. We introduce a "Fold" operation to improve the atrous convolution and form a novel folded atrous convolution.
  arXiv  Detail & Related papers  (2023-03-18T11:26:36Z)
• Publicly-Verifiable Deletion via Target-Collapsing Functions [81.13800728941818]
  We show that targetcollapsing enables publiclyverifiable deletion (PVD) We build on this framework to obtain a variety of primitives supporting publiclyverifiable deletion from weak cryptographic assumptions.
  arXiv  Detail & Related papers  (2023-03-15T15:00:20Z)
• Deep Neural Networks for Encrypted Inference with TFHE [0.0]
  Fully homomorphic encryption (FHE) is an encryption method that allows to perform computation on encrypted data, without decryption. TFHE preserves the privacy of the users of online services that handle sensitive data, such as health data, biometrics, credit scores and other personal information. We show how to construct Deep Neural Networks (DNNs) that are compatible with the constraints of TFHE, an FHE scheme that allows arbitrary depth computation circuits.
  arXiv  Detail & Related papers  (2023-02-13T09:53:31Z)
• BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance [54.214426436283134]
  Deep neural networks, such as the Deep-FSMN, have been widely studied for keyword spotting (KWS) applications. We present a strong yet efficient binary neural network for KWS, namely BiFSMNv2, pushing it to the real-network accuracy performance. We highlight that benefiting from the compact architecture and optimized hardware kernel, BiFSMNv2 can achieve an impressive 25.1x speedup and 20.2x storage-saving on edge hardware.
  arXiv  Detail & Related papers  (2022-11-13T18:31:45Z)
• THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption [112.02441503951297]
  Privacy-preserving inference of transformer models is on the demand of cloud service users. We introduce $textitTHE-X$, an approximation approach for transformers, which enables privacy-preserving inference of pre-trained models.
  arXiv  Detail & Related papers  (2022-06-01T03:49:18Z)
• FFConv: Fast Factorized Neural Network Inference on Encrypted Data [9.868787266501036]
  We propose a low-rank factorization method called FFConv to unify convolution and ciphertext packing. Compared to prior art LoLa and Falcon, our method reduces the inference latency by up to 87% and 12%, respectively.
  arXiv  Detail & Related papers  (2021-02-06T03:10:13Z)
• HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data [0.0]
  Homomorphic Encryption (HE) allows performing computation on encrypted data. We present a simple and intuitive framework that abstracts the packing decision for the user. We explain its underlying data structures and propose a novel algorithm for performing 2D operations.
  arXiv  Detail & Related papers  (2020-11-03T15:54:35Z)
• Suppress and Balance: A Simple Gated Network for Salient Object Detection [89.88222217065858]
  We propose a simple gated network (GateNet) to solve both issues at once. With the help of multilevel gate units, the valuable context information from the encoder can be optimally transmitted to the decoder. In addition, we adopt the atrous spatial pyramid pooling based on the proposed "Fold" operation (Fold-ASPP) to accurately localize salient objects of various scales.
  arXiv  Detail & Related papers  (2020-07-16T02:00:53Z)
• BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture [82.64881585566825]
  We present a novel Bi-directional O-shape network (BiO-Net) that reuses the building blocks in a recurrent manner without introducing any extra parameters. Our method significantly outperforms the vanilla U-Net as well as other state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-01T05:07:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.