{
  "abstract": "In response to the adversarial vulnerabilities of deep vision algorithms, existing security assessment methods often face problems such as low generation efficiency and severe visual distortion. It is urgent to explore a new paradigm for adversarial sample generation that takes into account high concealment and computational power economy. To this end, this paper aims to overcome the limitations of pixel-level iterative computation capabilities, eliminate biases in biological visual perception, and construct an adversarial example generation model based on latent space distribution search and cross-channel optimization techniques. This method uses a multi-layer convolutional auto-encoder as the base for dimensionality reduction, and maps the image matrix to a low-dimensional feature space for distribution search to extract adversarial priors. In terms of cross-channel quality optimization, by combining the human cone cell spectral sensing threshold and edge contour detection mask, perturbation isolation and precise location across color channels are implemented, and the counter-perturbation is covertly redistributed to visual low-sensitivity areas and high-frequency redundant areas. Experimental evaluation shows that this model maintains excellent visual fidelity while significantly reducing computing power overhead. The PSNR of adversarial samples reaches a maximum of 40.2 decibels. When the perturbation budget is increased to a standardized $$L_{\\infty }$$ norm constraint of 20/255, the perceptual distance metric remains at a low of 0.125. In actual black-box detection, the model’s migration penetration rate for the large unknown residual visual model reaches 78.5%, resulting in a sharp 88.0% drop in the median target prediction confidence. This paper not only provides a high-throughput automated vulnerability investigation tool for ubiquitous artificial intelligence vision applications, but also establishes a solid theoretical foundation for cross-channel physical isolation for robust boundary reconstruction of future defense systems.",
  "abstract_shown": true,
  "affiliations": [
    "Faculty of General Education, Zhejiang Agricultural Business College"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Yaoqin Sun"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cd41ebw5bjy6b.bib",
  "cited_by": 0,
  "doi": "10.1038/s41598-026-61365-1",
  "fulltext_url": "https://doi.org/10.1038/s41598-026-61365-1",
  "id": "cd41ebw5bjy6b",
  "issns": [
    "2045-2322"
  ],
  "landing_url": "https://doi.org/10.1038/s41598-026-61365-1",
  "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|Adversarial Robustness in Machine Learning"
    ]
  ],
  "openalex": "W7170801924",
  "pdf_url": "https://www.nature.com/articles/s41598-026-61365-1_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-01",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/cd41ebw5bjy6b.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:45:53Z",
      "native_id": "646c0ee24b1e4912aaa57d78f0c2f26d",
      "source": "doaj",
      "url": "https://doi.org/10.1038/s41598-026-61365-1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "lcc:R",
      "subfield": "general"
    }
  ],
  "title": "Efficient generation of adversarial examples and cross-channel quality optimization based on latent space distribution search",
  "title_text": "Efficient generation of adversarial examples and cross-channel quality optimization based on latent space distribution search",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T13:45:53Z",
  "url": "https://research.draconitic.com/paper/cd41ebw5bjy6b",
  "venue": "Scientific Reports",
  "versions": []
}