{"type":"ScholarlyArticle","title":"On Mitigating the Utility-Loss in Differentially Private Learning: A New Perspective by a Geometrically Inspired Kernel Approach (Abstract Reprint)","authors":[{"name":"Mohit Kumar","slug":"mohit-kumar","given":"Mohit","family":"Kumar","affiliation":"University of Rostock"},{"name":"Bernhard A. Moser","slug":"bernhard-a-moser","given":"Bernhard A.","family":"Moser","affiliation":"Johannes Kepler University Linz; Software Competence Center Hagenberg GmbH"},{"name":"Lukas Fischer","slug":"lukas-fischer","given":"Lukas","family":"Fischer","affiliation":"Software Competence Center Hagenberg GmbH"}],"abstract":"Privacy-utility tradeoff remains as one of the fundamental issues of differentially private machine learning. This paper introduces a geometrically inspired kernel-based approach to mitigate the accuracy-loss issue in classification. In this approach, a representation of the affine hull of given data points is learned in Reproducing Kernel Hilbert Spaces (RKHS). This leads to a novel distance measure that hides privacy-sensitive information about individual data points and improves the privacy-utility tradeoff via significantly reducing the risk of membership inference attacks. The effectiveness of the approach is demonstrated through experiments on MNIST dataset, Freiburg groceries dataset, and a real biomedical dataset. It is verified that the approach remains computationally practical. The application of the approach to federated learning is considered and it is observed that the accuracy-loss due to data being distributed is either marginal or not significantly high.","doi":"10.24963/ijcai.2024/952","url":"https://ijcai.org/proceedings/2024/952","pdf":"https://ijcai.org/proceedings/2024/0952.pdf","markdown":"https://ijcai.org/proceedings/2024/952.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/952","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Journal Track","track":"Journal Track","number":952,"pages":{"first":8480,"last":8480},"keywords":["Journal Track: Journal Track"],"videos":[],"references":[{"position":1,"raw":"[Kumar et al., 2024] Mohit Kumar, Bernhard Alois Moser, and Lukas Fischer. On mitigating the utility-loss in dif- ferentially private learning: A new perspective by a geo- metrically inspired kernel approach. J. Artif. Intell. Res., 79:515-567, 2024.","title":"On mitigating the utility-loss in differentially private learning: A new perspective by a geometrically inspired kernel approach","authors":"Mohit Kumar, Bernhard Alois Moser, Lukas Fischer","year":"2024","venue":"J. Artif. Intell. Res","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}