{
  "patent_number": "US 11544411",
  "country": "US",
  "title": "How to Check if an AI Model Has Been Tampered With",
  "original_title": "Machine learning model validation and authentication",
  "summary": "This patent describes a method to verify the integrity and authorized use of an artificial intelligence model by feeding it a special digital key and comparing its response to a known good one.",
  "what_it_does": "The patent outlines a method for validating and authenticating machine learning models. It works by first \"providing a digital key that is associated with a particular entity\" (Claim 1). This key is then \"applied as input across at least a portion of the trained machine learning model to generate one or more verification outputs\" (Claim 1). These outputs are then \"compared to one or more known verification outputs\" that were previously generated when the model was known to be uncompromised (Claim 1). If the comparison reveals a discrepancy, the system \"determining... that one or more parameters of the trained machine learning model have been compromised\" and then indicates this compromise (Claim 1). For example, a company providing an AI model for medical diagnosis could periodically feed it a unique digital key. If the model's response to this key changes from the expected output, it signals that the model might have been altered or misused.",
  "what_it_does_not_cover": [
    "Does not cover detecting model compromise without using a specific digital key as input to the model itself.",
    "Does not cover validation methods that only check the final output without comparing it to a known output generated by a prior application of the same key.",
    "Does not cover general cybersecurity measures for AI models that do not involve this specific input-output verification process.",
    "Does not cover methods that do not involve comparing outputs to *known* outputs generated by *prior* application of the digital key."
  ],
  "filed": "2020-01-14",
  "granted": "2023-01-03",
  "expires": "2040-01-14",
  "status": "active",
  "holder": "Koninklijke Philips NV",
  "holder_url": "https://patentbrief.org/company/koninklijke-philips-nv",
  "inventors": [
    {
      "name": "Shawn Arie Peter Stapleton",
      "url": "https://patentbrief.org/inventor/shawn-arie-peter-stapleton"
    },
    {
      "name": "Amir Mohammad Tahmasebi Maraghoosh",
      "url": "https://patentbrief.org/inventor/amir-mohammad-tahmasebi-maraghoosh"
    }
  ],
  "times_cited": 1,
  "tags": [
    "software",
    "ai_ml",
    "telecommunications",
    "consumer_electronics"
  ],
  "abstract": "The present disclosure is directed to methods and apparatus for validating and authenticating use of machine learning models. For example, various techniques are described herein to limit the vulnerability of machine learning models to attack and/or exploitation of the model for malicious use, and for detecting when such attack/exploitation has occurred. Additionally, various embodiments described herein promote the protection of sensitive and/or valuable data, for example by ensuring only licensed use is permissible. Moreover, techniques are described for version tracking, usage tracking, permission tracking, and evolution of machine learning models.",
  "url": "https://patentbrief.org/patent/us/11544411/machine-learning-model-validation-and-authentication",
  "markdown_url": "https://patentbrief.org/patent/us/11544411/machine-learning-model-validation-and-authentication/md",
  "google_patents_url": "https://patents.google.com/patent/US11544411",
  "relatedPatents": [
    {
      "patentNumber": "10599957",
      "countryCode": "US",
      "title": "How to Automatically Detect and Fix Changes in AI Model Data",
      "url": "https://patentbrief.org/patent/us/10599957/systems-and-methods-for-detecting-data-drift-for-data-used-in-machine-learning-m"
    },
    {
      "patentNumber": "11651227",
      "countryCode": "US",
      "title": "How to Force AI to Follow Logical Rules During Training",
      "url": "https://patentbrief.org/patent/us/11651227/muzero"
    },
    {
      "patentNumber": "20230044102",
      "countryCode": "US",
      "title": "Improving AI Predictions by Factoring in How Much You Trust Each Model",
      "url": "https://patentbrief.org/patent/us/20230044102/ensemble-machine-learning-models-incorporating-a-model-trust-factor"
    },
    {
      "patentNumber": "12518214",
      "countryCode": "US",
      "title": "Training AI on Private Data Without Seeing It",
      "url": "https://patentbrief.org/patent/us/12518214/distributed-machine-learning-systems-including-generation-of-synthetic-data"
    },
    {
      "patentNumber": "12443890",
      "countryCode": "US",
      "title": "How Devices Train Shared AI Models While Keeping Your Data Private",
      "url": "https://patentbrief.org/patent/us/12443890/partially-local-federated-learning"
    }
  ]
}