Covert Learning: How to Learn with an Untrusted Intermediary

Autor:	Ran Canetti, Ari Karchmer
Rok vydání:	2021
Předmět:	Class (computer programming) Computer science Human–computer interaction Process (engineering) Covert media_common.quotation_subject Function (engineering) Oracle media_common Task (project management)
Zdroj:	Theory of Cryptography ISBN: 9783030904555 TCC (3)
DOI:	10.1007/978-3-030-90456-2_1
Popis:	We consider the task of learning a function via oracle queries, where the queries and responses are monitored (and perhaps also modified) by an untrusted intermediary. Our goal is twofold: First, we would like to prevent the intermediary from gaining any information about either the function or the learner’s intentions (e.g. the particular hypothesis class the learner is considering). Second, we would like to curb the intermediary’s ability to meaningfully interfere with the learning process, even when it can modify the oracles’ responses.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::8e8012e674a9ce5c65c27a9db62f7b39 https://doi.org/10.1007/978-3-030-90456-2_1 Zobrazit plný text záznamu