Search

Find a vulnerability

Search criteria ⓘ Use this form to refine search results.
Full-text search supports keyword queries with ranking and filtering.
You can combine vendor, product, and sources to narrow results.
Enable “Apply ordering” to sort by date instead of relevance.

    1 vulnerability found for Kaspersky's Antimalware ML Model

    AVID-2023-V014

    Vulnerability from avid – Published: 2023-03-31 – Updated: 2023-03-31 ATLAS Case Study
    Summary
    Cloud storage and computations have become popular platforms for deploying ML malware detectors. In such cases, the features for models are built on users' systems and then sent to cybersecurity company servers. The Kaspersky ML research team explored this gray-box scenario and showed that feature knowledge is enough for an adversarial attack on ML models. They attacked one of Kaspersky's antimalware ML models without white-box access to it and successfully evaded detection for most of the adversarially modified malware files.
    Risk domain
    Security
    SEP view
    S0403: Adversarial Example
    Lifecycle
    L06: Deployment
    Organisations
    Kaspersky's Antimalware ML Model (deployer)
    Affected artifacts
    Artifact Type
    Kaspersky's Antimalware ML Model System
    References
    URL Label
    https://atlas.mitre.org/studies/AML.CS0014 Confusing Antimalware Neural Networks
    https://securelist.com/how-to-confuse-antimalware… Article, "How to confuse antimalware neural networks. Adversarial attacks and protection"
    To clipboard 

    {
  "affects": {
    "artifacts": [
      {
        "name": "Kaspersky\u0027s Antimalware ML Model",
        "type": "System"
      }
    ],
    "deployer": [
      "Kaspersky\u0027s Antimalware ML Model"
    ],
    "developer": []
  },
  "credit": null,
  "data_type": "AVID",
  "data_version": "0.2",
  "description": {
    "lang": "eng",
    "value": "Cloud storage and computations have become popular platforms for deploying ML malware detectors.\nIn such cases, the features for models are built on users\u0027 systems and then sent to cybersecurity company servers.\nThe Kaspersky ML research team explored this gray-box scenario and showed that feature knowledge is enough for an adversarial attack on ML models.\n\nThey attacked one of Kaspersky\u0027s antimalware ML models without white-box access to it and successfully evaded detection for most of the adversarially modified malware files."
  },
  "impact": {
    "avid": {
      "lifecycle_view": [
        "L06: Deployment"
      ],
      "risk_domain": [
        "Security"
      ],
      "sep_view": [
        "S0403: Adversarial Example"
      ],
      "taxonomy_version": "0.2"
    }
  },
  "last_modified_date": "2023-03-31",
  "metadata": {
    "vuln_id": "AVID-2023-V014"
  },
  "problemtype": {
    "classof": "ATLAS Case Study",
    "description": {
      "lang": "eng",
      "value": "Confusing Antimalware Neural Networks"
    },
    "type": "Advisory"
  },
  "published_date": "2023-03-31",
  "references": [
    {
      "label": "Confusing Antimalware Neural Networks",
      "type": "source",
      "url": "https://atlas.mitre.org/studies/AML.CS0014"
    },
    {
      "label": "Article, \"How to confuse antimalware neural networks. Adversarial attacks and protection\"",
      "type": "source",
      "url": "https://securelist.com/how-to-confuse-antimalware-neural-networks-adversarial-attacks-and-protection/102949/"
    }
  ],
  "reports": null
}