Homomorphic Encryptions for Privacy Preserving Vision

• URL: http://arxiv.org/abs/2606.25216v1
• Date: Tue, 23 Jun 2026 22:28:30 GMT
• Title: Homomorphic Encryptions for Privacy Preserving Vision
• Abstract summary: We aim to perform inference tasks in Computer Vision in a privacy-preserving manner, by only looking at encrypted data.<n>Applying homomorphic encryptions to CNNs requires modifying the conventional CNN layers, so that they adhere to the encryption scheme.<n>We successfully obtained minimal drop in classification accuracy for various datasets.
• Score: 1.4268073078103212
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Legal requirements might prevent organizations from sharing sensitive data like medical or financial details of consumers which prevents them from leveraging cloud based ML-as-a-service solutions provided by third party providers, which are quickly gaining popularity these days. In this project, we aim to perform inference tasks in Computer Vision in a privacy-preserving manner, i.e, by only looking at encrypted data. Recent advances in fully homomorphic encryption make this possible. A fully homomorphic encryption allows an arbitrary sequence of additive and multiplicative operations to be performed on encrypted data directly. Applying homomorphic encryptions to CNNs requires modifying the conventional CNN layers, so that they adhere to the encryption scheme. Our aim was to explore the best methods to create CNNs which can classify encrypted images directly. We used Microsoft SEAL for performing homomorphic encryption. The performance of these "encryption based CNNs" should be comparable with baseline accuracies of the same CNNs trained on unencrypted data, and the aim was to achieve as low of a hit on inference-time performance as possible. We successfully obtained minimal drop in classification accuracy for various datasets. We used MNIST as our baseline, which is popularly used in related research work and then explored more complex datasets like Kuzushiji MNIST, Fashion-MNIST and CIFAR-10 as a part of our contribution. Additionally, we also added support for more complex operations on top of TenSEAL, like processing colored images (multi-channel input), applying multiple convolutional layers and performing average pooling.

Related papers

• Training Machine Learning Models on Encrypted Data: A Privacy-Preserving Framework using Homomorphic Encryption [40.16348991707144]
  Homomorphic encryption enables computations on encrypted data without decryption, thus preserving confidentiality throughout the Machine Learning pipeline.<n>This paper addresses the challenge of training ML models on encrypted data while maintaining accuracy and efficiency.<n>It demonstrates the feasibility of training K-Nearest Neighbors (KNN) and linear regression models on encrypted data, and evaluates encrypted inference for a basic Multilayer Perceptron (MLP) architecture.
  arXiv  Detail & Related papers  (2026-04-25T10:50:41Z)
• HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption [3.0841649700901117]
  Fully Homomorphic Encryption (FHE) is an encryption scheme that not only encrypts data but also allows for computations to be applied directly on the encrypted data.<n>In this paper, we explore the challenges and opportunities when applying FHE to Deep Learning Recommendation Models (DLRM)<n>We develop novel methods for performing compressed embedding lookups in order to reduce FHE computational costs while keeping the underlying model performant.
  arXiv  Detail & Related papers  (2025-06-22T19:40:04Z)
• 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)
• Recoverable Privacy-Preserving Image Classification through Noise-like Adversarial Examples [26.026171363346975]
  Cloud-based image related services such as classification have become crucial. In this study, we propose a novel privacypreserving image classification scheme. encrypted images can be decrypted back into their original form with high fidelity (recoverable) using a secret key.
  arXiv  Detail & Related papers  (2023-10-19T13:01:58Z)
• Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryption [33.35896071292604]
  Training large-scale CNNs that during inference can be run under Homomorphic Encryption (HE) is challenging. We provide a novel training method for large CNNs such as ResNet-152 and ConvNeXt models.
  arXiv  Detail & Related papers  (2023-04-26T20:41:37Z)
• Verifiable Encodings for Secure Homomorphic Analytics [10.402772462535884]
  Homomorphic encryption is a promising solution for protecting privacy of cloud-delegated computations on sensitive data. We propose two error detection encodings and build authenticators that enable practical client-verification of cloud-based homomorphic computations. We implement our solution in VERITAS, a ready-to-use system for verification of outsourced computations executed over encrypted data.
  arXiv  Detail & Related papers  (2022-07-28T13:22:21Z)
• 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)
• Reinforcement Learning on Encrypted Data [58.39270571778521]
  We present a preliminary, experimental study of how a DQN agent trained on encrypted states performs in environments with discrete and continuous state spaces. Our results highlight that the agent is still capable of learning in small state spaces even in presence of non-deterministic encryption, but performance collapses in more complex environments.
  arXiv  Detail & Related papers  (2021-09-16T21:59:37Z)
• NeuraCrypt: Hiding Private Health Data via Random Neural Networks for Public Training [64.54200987493573]
  We propose NeuraCrypt, a private encoding scheme based on random deep neural networks. NeuraCrypt encodes raw patient data using a randomly constructed neural network known only to the data-owner. We show that NeuraCrypt achieves competitive accuracy to non-private baselines on a variety of x-ray tasks.
  arXiv  Detail & Related papers  (2021-06-04T13:42:21Z)
• Highly Accurate CNN Inference Using Approximate Activation Functions over Homomorphic Encryption [0.1933681537640272]
  A common method of handling sensitive data in the cloud uses homomorphic encryption, which allows computation over encrypted data without decryption. Previous research usually adopted a low-degree mapping function, such as the square function, for data classification. We implement CNN inference over homomorphic encryption using the Microsoft's Simple Encrypted Arithmetic Library for the Cheon-Kim-Kim-Song scheme.
  arXiv  Detail & Related papers  (2020-09-08T13:20:59Z)
• HERS: Homomorphically Encrypted Representation Search [56.87295029135185]
  We present a method to search for a probe (or query) image representation against a large gallery in the encrypted domain. Our encryption scheme is agnostic to how the fixed-length representation is obtained and can therefore be applied to any fixed-length representation in any application domain.
  arXiv  Detail & Related papers  (2020-03-27T01:10:54Z)
• CryptoSPN: Privacy-preserving Sum-Product Network Inference [84.88362774693914]
  We present a framework for privacy-preserving inference of sum-product networks (SPNs) CryptoSPN achieves highly efficient and accurate inference in the order of seconds for medium-sized SPNs.
  arXiv  Detail & Related papers  (2020-02-03T14:49:18Z)

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.