{
  "abstract": "The widespread adoption of cloud-based Machine Learning as a Service (MLaaS) exposes sensitive user data to critical privacy risks during inference, as plaintext data must typically be processed by untrusted cloud servers. This paper presents HE-CloudML, a unified privacy-preserving framework for secure deep neural network (DNN) inference over encrypted cloud data using Homomorphic Encryption (HE). HE-CloudML is architected as a three-tier system comprising a client-side CKKS encryption module, a cloud-side HE inference engine, and a key management layer, ensuring that raw input data is never exposed to the server at any stage of computation. The framework introduces HE-compatible polynomial activation function approximations via degree-5 Chebyshev minimax polynomials, an optimized SIMD ciphertext batching strategy exploiting Ring Learning With Errors (RLWE) slot packing, and an adaptive lazy bootstrapping pipeline to substantially reduce homomorphic evaluation depth and inference latency. A formal security analysis under the IND-CPA model grounded in the RLWE hardness assumption shows that the cloud server cannot distinguish, and therefore cannot recover, the plaintext input, intermediate activations, or output from the ciphertexts it observes; this argument covers a semi-honest server and does not by itself establish resistance to active/malicious-server, model-inversion, or membership-inference attacks, which remain future work. Comprehensive experiments across three domains benchmark image classification (MNIST: 99.28%, CIFAR-10: 90.37%), medical imaging (93.61%), and financial fraud detection (96.44%) demonstrate that HE-CloudML achieves near-plaintext accuracy with a maximum accuracy drop of 1.81%, while delivering up to 26.9× latency improvements over CryptoNets.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Computer Science, Faculty of Computing, SIMAD University Mogadishu"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Abdullahi Ahmed Abdirahman"
    },
    {
      "affs": [
        0
      ],
      "name": "Abdirahman Osman Hashi"
    },
    {
      "affs": [
        0
      ],
      "name": "Ubaid Mohamed Dahir"
    },
    {
      "affs": [
        0
      ],
      "name": "Mohamed Abdirahman Elmi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0babwp3shk8j2.bib",
  "cited_by": 1,
  "doi": "10.1038/s41598-026-69466-7",
  "fulltext_url": "https://doi.org/10.1038/s41598-026-69466-7",
  "id": "0babwp3shk8j2",
  "issns": [
    "2045-2322"
  ],
  "landing_url": "https://doi.org/10.1038/s41598-026-69466-7",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "Q"
    ],
    [
      "lcc",
      "R"
    ],
    [
      "openalex",
      "1702|Cryptography and Data Security"
    ]
  ],
  "openalex": "W7165904573",
  "pdf_url": "https://www.nature.com/articles/s41598-026-69466-7_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/0babwp3shk8j2.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:45:57Z",
      "native_id": "39e95d86993a43d4afbcb11dee3a0c87",
      "source": "doaj",
      "url": "https://doi.org/10.1038/s41598-026-69466-7"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "lcc:R",
      "subfield": "general"
    }
  ],
  "title": "HE-CloudML: a privacy-preserving framework for secure machine learning inference over encrypted cloud data using homomorphic encryption",
  "title_text": "HE-CloudML: a privacy-preserving framework for secure machine learning inference over encrypted cloud data using homomorphic encryption",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T13:45:57Z",
  "url": "https://research.draconitic.com/paper/0babwp3shk8j2",
  "venue": "Scientific Reports",
  "versions": []
}