{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-12001588","patent":{"patent_number":"US-12001588","title":"Interpretability framework for differentially private deep learning","assignee":null,"inventors":[],"filing_date":"2020-10-30T00:00:00.000Z","publication_date":"2024-06-04T00:00:00.000Z","cpc_codes":["G06F","G06F","G06F","G06F","G06F","G06N","G06N"],"num_claims":7,"abstract":"Data is received that specifies a bound for an adversarial posterior belief ρc that corresponds to a likelihood to re-identify data points from the dataset based on a differentially private function output. Privacy parameters ε, δ are then calculated based on the received data that govern a differential privacy (DP) algorithm to be applied to a function to be evaluated over a dataset. The calculating is based on a ratio of probabilities distributions of different observations, which are bound by the posterior belief ρc as applied to a dataset. The calculated privacy parameters are then used to apply the DP algorithm to the function over the dataset. Related apparatus, systems, techniques and articles are also described."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Interpretability framework for differentially private deep learning","description":"Data is received that specifies a bound for an adversarial posterior belief ρc that corresponds to a likelihood to re-identify data points from the dataset based on a differentially private function o","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-12001588","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-12001588","citation_suggestion":"Patentable. \"Interpretability framework for differentially private deep learning\" (US-12001588). https://patentable.app/patents/US-12001588","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-12001588","json":"https://patentable.app/api/llm-context/US-12001588","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T09:35:29.957Z"}