Encrypted Vector Similarity Computations Using Partially Homomorphic Encryption: Applications and Performance Analysis

• URL: http://arxiv.org/abs/2503.05850v1
• Date: Fri, 07 Mar 2025 09:52:16 GMT
• Title: Encrypted Vector Similarity Computations Using Partially Homomorphic Encryption: Applications and Performance Analysis
• Authors: Sefik Serengil, Alper Ozpinar,
• Abstract summary: We show encrypted cosine similarity can be computed using partially homomorphic encryption (PHE)<n>PHE is less computationally intensive, faster, and produces smaller ciphertexts/keys.<n>Results show PHE is well-suited for memory-constrained environments and real-world privacy-preserving encrypted similarity search.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper explores the use of partially homomorphic encryption (PHE) for encrypted vector similarity search, with a focus on facial recognition and broader applications like reverse image search, recommendation engines, and large language models (LLMs). While fully homomorphic encryption (FHE) exists, we demonstrate that encrypted cosine similarity can be computed using PHE, offering a more practical alternative. Since PHE does not directly support cosine similarity, we propose a method that normalizes vectors in advance, enabling dot product calculations as a proxy. We also apply min-max normalization to handle negative dimension values. Experiments on the Labeled Faces in the Wild (LFW) dataset use DeepFace's FaceNet128d, FaceNet512d, and VGG-Face (4096d) models in a two-tower setup. Pre-encrypted embeddings are stored in one tower, while an edge device captures images, computes embeddings, and performs encrypted-plaintext dot products via additively homomorphic encryption. We implement this with LightPHE, evaluating Paillier, Damgard-Jurik, and Okamoto-Uchiyama schemes, excluding others due to performance or decryption complexity. Tests at 80-bit and 112-bit security (NIST-secure until 2030) compare PHE against FHE (via TenSEAL), analyzing encryption, decryption, operation time, cosine similarity loss, key/ciphertext sizes. Results show PHE is less computationally intensive, faster, and produces smaller ciphertexts/keys, making it well-suited for memory-constrained environments and real-world privacy-preserving encrypted similarity search.

Related papers

• The Beginner's Textbook for Fully Homomorphic Encryption [1.6679662639178265]
  Fully Homomorphic Encryption (FHE) is a cryptographic scheme that enables computations to be performed directly on encrypted data. After all computations are performed on the encrypted data, it can be decrypted to reveal the result. FHE can be applied to confidential blockchain services, ensuring that sensitive data in smart contracts remains encrypted and confidential.
  arXiv  Detail & Related papers  (2025-03-07T04:29:11Z)
• CipherFace: A Fully Homomorphic Encryption-Driven Framework for Secure Cloud-Based Facial Recognition [0.0]
  This paper introduces CipherFace, a homomorphic encryption-driven framework for secure cloud-based facial recognition.<n>By leveraging FHE, CipherFace ensures the privacy of embeddings while utilizing the cloud for efficient distance computation.<n>We propose a novel encrypted distance computation method for both Euclidean and Cosine, addressing key challenges in performing secure similarity calculations on encrypted data.
  arXiv  Detail & Related papers  (2025-02-22T19:03:04Z)
• A Note on Efficient Privacy-Preserving Similarity Search for Encrypted Vectors [1.3824176915623292]
  Traditional approaches to vector similarity search over encrypted data rely on fully homomorphic encryption (FHE) to enable computation without decryption.<n>This work explores a more efficient alternative: using additively homomorphic encryption (AHE) for privacy-preserving similarity search.<n>We present an efficient algorithm for encrypted similarity search under AHE and analyze its error growth and security implications.
  arXiv  Detail & Related papers  (2025-02-20T06:07:04Z)
• Secure Semantic Communication With Homomorphic Encryption [52.5344514499035]
  This paper explores the feasibility of applying homomorphic encryption to SemCom. We propose a task-oriented SemCom scheme secured through homomorphic encryption.
  arXiv  Detail & Related papers  (2025-01-17T13:26:14Z)
• SOCI^+: An Enhanced Toolkit for Secure OutsourcedComputation on Integers [50.608828039206365]
  We propose SOCI+ which significantly improves the performance of SOCI. SOCI+ employs a novel (2, 2)-threshold Paillier cryptosystem with fast encryption and decryption as its cryptographic primitive. Compared with SOCI, our experimental evaluation shows that SOCI+ is up to 5.4 times more efficient in computation and 40% less in communication overhead.
  arXiv  Detail & Related papers  (2023-09-27T05:19:32Z)
• Memorization for Good: Encryption with Autoregressive Language Models [8.645826579841692]
  We propose the first symmetric encryption algorithm with autoregressive language models (SELM) We show that autoregressive LMs can encode arbitrary data into a compact real-valued vector (i.e., encryption) and then losslessly decode the vector to the original message (i.e. decryption) via random subspace optimization and greedy decoding.
  arXiv  Detail & Related papers  (2023-05-15T05:42:34Z)
• 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)
• RiDDLE: Reversible and Diversified De-identification with Latent Encryptor [57.66174700276893]
  This work presents RiDDLE, short for Reversible and Diversified De-identification with Latent Encryptor. Built upon a pre-learned StyleGAN2 generator, RiDDLE manages to encrypt and decrypt the facial identity within the latent space.
  arXiv  Detail & Related papers  (2023-03-09T11:03:52Z)
• HEFT: Homomorphically Encrypted Fusion of Biometric Templates [20.10175446213924]
  We propose a non-interactive solution for secure fusion and matching of biometric templates using fully homomorphic encryption (FHE) Our method, dubbed HEFT, is custom-designed to overcome the unique constraint imposed FHE, namely the lack of computation support for non-arithmetic operations. Experimental evaluation for template fusion shows that HEFT (i) improves biometric verification performance by 11.07% and 9.58% AUROC compared to the respective unibiometric representations.
  arXiv  Detail & Related papers  (2022-08-15T14:55:08Z)
• 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)
• 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)

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.