DAAP: Privacy-Preserving Model Accuracy Estimation on Unlabeled Datasets Through Distribution-Aware Adversarial Perturbation

TitleDAAP: Privacy-Preserving Model Accuracy Estimation on Unlabeled Datasets Through Distribution-Aware Adversarial Perturbation
Publication TypeConference Paper
Year of Publication2024
AuthorsCao G, Wang Z, Feng Y, Dong X
Conference Name33rd USENIX Security Symposium (USENIX Security 24)
Date Published08/2024
PublisherUSENIX Association
Conference LocationPhiladelphia, PA
ISBN Number978-1-939133-44-1
URLhttps://www.usenix.org/conference/usenixsecurity24/presentation/cao-guodong