{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11481617","patent":{"patent_number":"US-11481617","title":"Generating trained neural networks with increased robustness against adversarial attacks","assignee":null,"inventors":[],"filing_date":"2019-01-22T00:00:00.000Z","publication_date":"2022-10-25T00:00:00.000Z","cpc_codes":["G06N","G06N","G06F","G06N","G06N","G06N","H04L"],"num_claims":9,"abstract":"The present disclosure relates to systems, methods, and non-transitory computer readable media for generating trained neural network with increased robustness against adversarial attacks by utilizing a dynamic dropout routine and/or a cyclic learning rate routine. For example, the disclosed systems can determine a dynamic dropout probability distribution associated with neurons of a neural network. The disclosed systems can further drop neurons from a neural network based on the dynamic dropout probability distribution to help neurons learn distinguishable features. In addition, the disclosed systems can utilize a cyclic learning rate routine to force copy weights of a copy neural network away from weights of an original neural network without decreasing prediction accuracy to ensure that the decision boundaries learned are different."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Generating trained neural networks with increased robustness against adversarial attacks","description":"The present disclosure relates to systems, methods, and non-transitory computer readable media for generating trained neural network with increased robustness against adversarial attacks by utilizing ","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11481617","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-11481617","citation_suggestion":"Patentable. \"Generating trained neural networks with increased robustness against adversarial attacks\" (US-11481617). https://patentable.app/patents/US-11481617","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11481617","json":"https://patentable.app/api/llm-context/US-11481617","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T16:57:46.375Z"}