手法を比較

	安全多方计算	差分プライバシー	Federated Learning（連合学習）	k匿名性：公開データにおける個人プライバシーの保護
分野	プライバシー	プライバシー	プライバシー	プライバシー
系統	Machine learning	Machine learning	Machine learning	Machine learning
提唱年	1982	2006	2017	2002
提唱者	Andrew Yao	Cynthia Dwork	McMahan et al.	Latanya Sweeney
種類	Cryptographic protocol family	Privacy-preserving randomized mechanism	Distributed privacy-preserving machine learning	Privacy-preserving data transformation
原典	Yao, A. C. (1982). Protocols for secure computations. 23rd Annual Symposium on Foundations of Computer Science, 160–164.	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.	Sweeney, L. (2002). k-anonymity: A model for protecting privacy. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 10(5), 557–570.
別名	MPC, Multi-Party Computation, Privacy-Preserving Computation, Güvenli Çok Taraflı Hesaplama	DP, epsilon-differential privacy, randomized privacy, Diferansiyel Gizlilik	Collaborative Learning, Decentralized Learning, FedAvg, Federe Öğrenme	k-Anonymization, k-Anonymous Microdata, Quasi-Identifier Suppression Model, k-Anonimlik
関連	3	3	3	2
概要	Secure Multi-Party Computation (SMPC) is a cryptographic paradigm that enables two or more parties to jointly compute a function over their private inputs without revealing those inputs to one another. Introduced by Andrew Yao in 1982 through his seminal garbled-circuit construction, SMPC provides provable privacy guarantees grounded in computational hardness assumptions. It underpins modern privacy-preserving data analysis, enabling collaborative computation on sensitive datasets in finance, healthcare, and machine learning.	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.	k-Anonymity is a formal privacy model introduced by Latanya Sweeney in 2002 to protect individuals when personal data is released for research or public use. It requires that every record in a published dataset be indistinguishable from at least k−1 other records with respect to a designated set of quasi-identifying attributes — such as age, gender, and ZIP code — preventing re-identification by linking released data to external sources.