{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11514297","patent":{"patent_number":"US-11514297","title":"Post-training detection and identification of human-imperceptible backdoor-poisoning attacks","assignee":null,"inventors":[],"filing_date":"2020-05-27T00:00:00.000Z","publication_date":"2022-11-29T00:00:00.000Z","cpc_codes":["G06F","G06N","G06N","G06N","G06F"],"num_claims":18,"abstract":"This patent concerns novel technology for detecting backdoors of neural network, particularly deep neural network (DNN), classifiers. The backdoors are planted by suitably poisoning the training dataset, i.e., a data-poisoning attack. Once added to input samples from a source class (or source classes), the backdoor pattern causes the decision of the neural network to change to a target class. The backdoors under consideration are small in norm so as to be imperceptible to a human, but this does not limit their location, support or manner of incorporation. There may not be components (edges, nodes) of the DNN which are dedicated to achieving the backdoor function. Moreover, the training dataset used to learn the classifier may not be available. In one embodiment of the present invention which addresses such challenges, if the classifier is poisoned then the backdoor pattern is determined through a feasible optimization process, followed by an inference process, so that both the backdoor pattern itself and the associated source class(es) and target class are determined based only on the classifier parameters and a set of clean (unpoisoned attacked) samples from the different classes (none of which may be training samples)."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Post-training detection and identification of human-imperceptible backdoor-poisoning attacks","description":"This patent concerns novel technology for detecting backdoors of neural network, particularly deep neural network (DNN), classifiers. The backdoors are planted by suitably poisoning the training datas","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11514297","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-11514297","citation_suggestion":"Patentable. \"Post-training detection and identification of human-imperceptible backdoor-poisoning attacks\" (US-11514297). https://patentable.app/patents/US-11514297","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11514297","json":"https://patentable.app/api/llm-context/US-11514297","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T21:00:53.984Z"}