{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11501212","patent":{"patent_number":"US-11501212","title":"Method for protecting a machine learning model against extraction","assignee":null,"inventors":[],"filing_date":"2020-04-21T00:00:00.000Z","publication_date":"2022-11-15T00:00:00.000Z","cpc_codes":["G06N","G06F","G06F"],"num_claims":20,"abstract":"A method for protecting a first machine learning (ML) model is provided. In the method, a dataset of non-problem domain (NPD) data is selected from a large dataset using a second ML model. The second ML model classifies the large dataset into NPD classifications and PD classifications. The PD classified data is excluded. A distinguisher includes a third ML model that is trained using selected NPD data from the large dataset. The distinguisher receives input samples that are intended for the first ML model. The third ML model provides either a PD classification or NPD classification in response to receiving each input sample. An indication of a likely extraction attempt may be provided when a predetermined number of NPD classifications are provided. The method provides an efficient way to create a training dataset for a distinguisher and for protecting a ML model with the distinguisher."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Method for protecting a machine learning model against extraction","description":"A method for protecting a first machine learning (ML) model is provided. In the method, a dataset of non-problem domain (NPD) data is selected from a large dataset using a second ML model. The second ","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11501212","license":"CC-BY-4.0-like","license_terms":"AI-generated analysis on this page (summary, layman_explanation, technical_analysis, business_analysis, faqs) may be reused with attribution and a visible link back to the canonical URL above. Patent abstracts, claims, and bibliographic data are USPTO public domain.","required_link":"https://patentable.app/patents/US-11501212","citation_suggestion":"Patentable. \"Method for protecting a machine learning model against extraction\" (US-11501212). https://patentable.app/patents/US-11501212","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11501212","json":"https://patentable.app/api/llm-context/US-11501212","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T14:06:35.483Z"}