Robust and Interpretable Chest X-ray Classification via Diffusion Purification and Concept-Based Adversarial Detection.

Adversarial attack is an approach that primarily compromise the integrity of deep learning system in medical imaging by adding subtle changes to the model inputs that humans don't notice, it leads the model to make an incorrect decision, so the attacker can corrupt both the input data and the predic...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Basrah Researches (Sciences) Vol. 51; no. 2; pp. 270 - 284
Autor principal: Ali, Amna Kadhim
Formato: Artículo
Publicado: Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) 2025
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=191821471&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 191821471
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        18172695
        GYGY
      jtl: Journal of Basrah Researches (Sciences)
      issn: 18172695
      maglogo: N
    pubinfo:
      dt: 2025
      vid: 51
      iid: 2
      pid: 25427
      pub: Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR)
    artinfo:
      ui:
        191821471
        10.56714/bjrs.51.2.19
      ppf: 270
      ppct: 14
      formats:
      tig:
        atl: Robust and Interpretable Chest X-ray Classification via Diffusion Purification and Concept-Based Adversarial Detection.
      aug:
        au: Ali, Amna Kadhim
        affil: College of Veterinary medicine, University of Basrah, Basrah, Iraq.
      su:
        Chest X rays
        Adversarial machine learning
        Image denoising
        Random forest algorithms
        Feature extraction
        Convolutional neural networks
        Ensemble learning
        Deep learning
      sug:
        subj:
          Chest X rays
          Adversarial machine learning
          Image denoising
          Random forest algorithms
          Feature extraction
          Convolutional neural networks
          Ensemble learning
          Deep learning
      keyword:
        Concept Activation Vectors (TCAV)
        Medical Images
        Random Forest
        Resnet18
        الصور الطبية
        (TCAV)
        Concept Activation Vectors
      ab: Adversarial attack is an approach that primarily compromise the integrity of deep learning system in medical imaging by adding subtle changes to the model inputs that humans don't notice, it leads the model to make an incorrect decision, so the attacker can corrupt both the input data and the prediction system. In this paper A hybrid detection method based on diffusion purification, deep feature extraction, and ensemble learning has been proposed to address this issue using chest x-ray images. Two phases make it up. First, cleansing the adversarial samples. This is accomplished by a diffusion model. The samples are regenerated to remove the small perturbations fully. In the second phase, the images are categorized into two groups. Clean and purified images are collected in a safe category, while harmful images are unsafe category. In the second stage, we utilize a pre-trained ResNet18 feature extractor to retrieve salient from chest X-rays. Furthermore, a Random Forest model classifies the features obtained from the ResNet18 model into harmful and non-harmful image. The experimental results show that the proposed framework can detect more than 99% of adversarial samples. The satisfactory detection rate of the proposed purification and ensemble-based feature detection for making AI-assisted disease detection more reliable and safer.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2025
    holdings:
      @attributes:
        islocal: N