{
  "patent_number": "US 11886579",
  "country": "US",
  "title": "How to Secure a Machine Learning Model with Encryption and Output Checks",
  "original_title": "Machine learning model validation and authentication",
  "summary": "This patent describes a method for protecting a machine learning model and its data by encrypting both, running calculations on the encrypted information, and then checking the decrypted results to see if the model has been tampered with.",
  "what_it_does": "This patent details a system and method for validating and authenticating machine learning models. It works by first providing a unique encryption key linked to a specific user or entity. Then, it encrypts the internal workings (parameters) of a trained machine learning model using this key, as described in claim 1. It also encrypts the data that will be fed into the model. Crucially, the encrypted input data is then processed by the encrypted model to produce an encrypted result. This encrypted result is then decrypted, and the system analyzes this decrypted output. The analysis checks if the output matches an expected structure, such as values falling within a certain range or adding up to a specific number (claims 4-6). If the output doesn't match, the system determines that the model's parameters have been compromised and alerts the user.",
  "what_it_does_not_cover": [
    "Does not cover systems where only the input data is encrypted, but the machine learning model itself is not.",
    "Does not cover systems where only the machine learning model's parameters are encrypted, but the input data is not.",
    "Does not cover methods of detecting model compromise that do not involve analyzing the decrypted output for structural compliance.",
    "Does not cover general model authentication that doesn't use the specific sequence of encrypting both model and data, processing, decrypting, and then analyzing the output for expected characteristics.",
    "Does not cover detecting model compromise by directly inspecting the encrypted model's parameters without processing data through it."
  ],
  "filed": "2020-01-13",
  "granted": "2024-01-30",
  "expires": "2040-01-13",
  "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": 0,
  "tags": [
    "software",
    "ai_ml",
    "telecommunications",
    "consumer_electronics",
    "biotech"
  ],
  "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/11886579/machine-learning-model-validation-and-authentication-11886579",
  "markdown_url": "https://patentbrief.org/patent/us/11886579/machine-learning-model-validation-and-authentication-11886579/md",
  "google_patents_url": "https://patents.google.com/patent/US11886579",
  "relatedPatents": []
}