So sánh phương pháp

	Quyền riêng tư vi phân	Học liên kết	Tạo dữ liệu tổng hợp để kiểm soát tiết lộ
Lĩnh vực	Quyền riêng tư	Quyền riêng tư	Quyền riêng tư
Họ	Machine learning	Machine learning	Machine learning
Năm ra đời	2006	2017	1993
Người khởi xướng	Cynthia Dwork	McMahan et al.	Donald Rubin
Loại	Privacy-preserving randomized mechanism	Distributed privacy-preserving machine learning	Privacy-preserving data synthesis
Công trình gốc	Dwork, C. (2006). Differential privacy. International Colloquium on Automata, Languages and Programming (ICALP), 1–12.	McMahan, B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. Artificial Intelligence and Statistics, 1273–1282.	Rubin, D. B. (1993). Statistical disclosure limitation. Journal of Official Statistics, 9(2), 461–468.
Tên gọi khác	DP, epsilon-differential privacy, randomized privacy, Diferansiyel Gizlilik	Collaborative Learning, Decentralized Learning, FedAvg, Federe Öğrenme	Fully Synthetic Data, Partial Synthetic Data, Statistical Data Synthesis, Sentetik Veri Üretimi
Liên quan	3	3	3
Tóm tắt	Differential privacy is a mathematical framework for releasing statistical information about a dataset while providing rigorous guarantees that individual records cannot be identified or inferred. Introduced by Cynthia Dwork in 2006, it formalizes privacy as a probabilistic bound: any single individual's presence or absence in the dataset changes the output distribution by at most a multiplicative factor of e^ε, where ε is the privacy budget controlling the privacy–utility tradeoff.	Federated Learning is a distributed machine learning paradigm introduced by McMahan et al. in 2017 in which a global model is trained collaboratively across multiple decentralized clients — such as mobile devices or hospital systems — without ever transferring raw data to a central server. Each participant computes model updates locally using its private data; only those updates, not the underlying data, are communicated and aggregated by the server to improve the shared model.	Synthetic data generation is a statistical disclosure limitation technique introduced by Donald Rubin in 1993, in which values in a confidential dataset are replaced by draws from a fitted posterior predictive distribution rather than released directly. The resulting artificial records preserve the joint statistical structure of the original data while preventing the identification of real individuals, enabling analysts to work with a publicly releasable dataset that behaves like the original for most inferential purposes.