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 ML-based Android Apps

    AVID-2023-V013

    Vulnerability from avid – Published: 2023-03-31 – Updated: 2023-03-31 ATLAS Case Study
    Summary
    Deep learning models are increasingly used in mobile applications as critical components. Researchers from Microsoft Research demonstrated that many deep learning models deployed in mobile apps are vulnerable to backdoor attacks via "neural payload injection." They conducted an empirical study on real-world mobile deep learning apps collected from Google Play. They identified 54 apps that were vulnerable to attack, including popular security and safety critical applications used for cash recognition, parental control, face authentication, and financial services.
    Risk domain
    Security
    SEP view
    S0201: Model Compromise, S0601: Ingest Poisoning, S0403: Adversarial Example
    Lifecycle
    L06: Deployment, L04: Model Development
    Organisations
    ML-based Android Apps (deployer)
    Affected artifacts
    Artifact Type
    ML-based Android Apps System
    References
    URL Label
    https://atlas.mitre.org/studies/AML.CS0013 Backdoor Attack on Deep Learning Models in Mobile Apps
    https://arxiv.org/abs/2101.06896 DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection
    To clipboard 

    {
  "affects": {
    "artifacts": [
      {
        "name": "ML-based Android Apps",
        "type": "System"
      }
    ],
    "deployer": [
      "ML-based Android Apps"
    ],
    "developer": []
  },
  "credit": null,
  "data_type": "AVID",
  "data_version": "0.2",
  "description": {
    "lang": "eng",
    "value": "Deep learning models are increasingly used in mobile applications as critical components.\nResearchers from Microsoft Research demonstrated that many deep learning models deployed in mobile apps are vulnerable to backdoor attacks via \"neural payload injection.\"\nThey conducted an empirical study on real-world mobile deep learning apps collected from Google Play. They identified 54 apps that were vulnerable to attack, including popular security and safety critical applications used for cash recognition, parental control, face authentication, and financial services."
  },
  "impact": {
    "avid": {
      "lifecycle_view": [
        "L06: Deployment",
        "L04: Model Development"
      ],
      "risk_domain": [
        "Security"
      ],
      "sep_view": [
        "S0201: Model Compromise",
        "S0601: Ingest Poisoning",
        "S0403: Adversarial Example"
      ],
      "taxonomy_version": "0.2"
    }
  },
  "last_modified_date": "2023-03-31",
  "metadata": {
    "vuln_id": "AVID-2023-V013"
  },
  "problemtype": {
    "classof": "ATLAS Case Study",
    "description": {
      "lang": "eng",
      "value": "Backdoor Attack on Deep Learning Models in Mobile Apps"
    },
    "type": "Advisory"
  },
  "published_date": "2023-03-31",
  "references": [
    {
      "label": "Backdoor Attack on Deep Learning Models in Mobile Apps",
      "type": "source",
      "url": "https://atlas.mitre.org/studies/AML.CS0013"
    },
    {
      "label": "DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection",
      "type": "source",
      "url": "https://arxiv.org/abs/2101.06896"
    }
  ],
  "reports": null
}