{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11977626","patent":{"patent_number":"US-11977626","title":"Securing machine learning models against adversarial samples through backdoor misclassification","assignee":null,"inventors":[],"filing_date":"2021-06-09T00:00:00.000Z","publication_date":"2024-05-07T00:00:00.000Z","cpc_codes":["G06F","G06F","G06F","G06N","G06N","G06V","G06V","G06F","G06N"],"num_claims":15,"abstract":"A method for securing a genuine machine learning model against adversarial samples includes the steps of attaching a trigger to a sample to be classified and classifying the sample with the trigger attached using a backdoored model that has been backdoored using the trigger. In a further step, it is determined whether an output of the backdoored model is the same as a backdoor class of the backdoored model, and/or an outlier detection method is applied to logits compared to honest logits that were computed using a genuine sample. These steps are repeated using different triggers and backdoored models respectively associated therewith. It is compared a number of times that an output of the backdoored models is not the same as the respective backdoor class, and/or a difference determined by applying the outlier detection method, against one or more thresholds so as to determine whether the sample is adversarial."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Securing machine learning models against adversarial samples through backdoor misclassification","description":"A method for securing a genuine machine learning model against adversarial samples includes the steps of attaching a trigger to a sample to be classified and classifying the sample with the trigger at","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11977626","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-11977626","citation_suggestion":"Patentable. \"Securing machine learning models against adversarial samples through backdoor misclassification\" (US-11977626). https://patentable.app/patents/US-11977626","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11977626","json":"https://patentable.app/api/llm-context/US-11977626","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T06:07:31.204Z"}