{"type":"ScholarlyArticle","title":"Hiding Numerical Vectors in Local Private and Shuffled Messages","authors":[{"name":"Shaowei Wang","slug":"shaowei-wang","given":"Shaowei","family":"Wang","affiliation":""},{"name":"Jin Li","slug":"jin-li","given":"Jin","family":"Li","affiliation":""},{"name":"Yuqiu Qian","slug":"yuqiu-qian","given":"Yuqiu","family":"Qian","affiliation":""},{"name":"Jiachun Du","slug":"jiachun-du","given":"Jiachun","family":"Du","affiliation":""},{"name":"Wenqing Lin","slug":"wenqing-lin","given":"Wenqing","family":"Lin","affiliation":""},{"name":"Wei Yang","slug":"wei-yang","given":"Wei","family":"Yang","affiliation":""}],"abstract":"Numerical vector aggregation has numerous applications in privacy-sensitive scenarios, such as distributed gradient estimation in federated learning, and statistical analysis on key-value data. Within the framework of local differential privacy, this work gives tight minimax error bounds of O(d s/(n epsilon^2)), where d is the dimension of the numerical vector and s is the number of non-zero entries. An attainable mechanism is then designed to improve from existing approaches suffering error rate of O(d^2/(n epsilon^2)) or O(d s^2/(n epsilon^2)). To break the error barrier in the local privacy, this work further consider privacy amplification in the shuffle model with anonymous channels, and shows the mechanism satisfies centralized (14 ln(2/delta) (s e^epsilon+2s-1)/(n-1))^0.5, delta)-differential privacy, which is domain independent and thus scales to federated learning of large models. We experimentally validate and compare it with existing approaches,  and demonstrate its significant error reduction.","doi":"10.24963/ijcai.2021/510","url":"https://ijcai.org/proceedings/2021/510","pdf":"https://ijcai.org/proceedings/2021/0510.pdf","markdown":"https://ijcai.org/proceedings/2021/510.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/510","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Multidisciplinary Topics and Applications","track":"Main Track","number":510,"pages":{"first":3706,"last":3712},"keywords":["Multidisciplinary Topics and Applications: Security and Privacy"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}