手法を比較

	Homomorphic Encryption	差分プライバシー	安全多方计算
分野	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
提唱年	2009	2006	1982
提唱者	Craig Gentry	Cynthia Dwork	Andrew Yao
種類	Lattice-based cryptographic scheme	Privacy-preserving randomized mechanism	Cryptographic protocol family
原典	Gentry, C. (2009). Fully homomorphic encryption using ideal lattices. ACM Symposium on Theory of Computing (STOC), 169–178.	Dwork, C. (2006). Differential privacy. International Colloquium on Automata, Languages and Programming (ICALP), 1–12.	Yao, A. C. (1982). Protocols for secure computations. 23rd Annual Symposium on Foundations of Computer Science, 160–164.
別名	FHE, Fully Homomorphic Encryption, Leveled Homomorphic Encryption, Homomorfik Şifreleme	DP, epsilon-differential privacy, randomized privacy, Diferansiyel Gizlilik	MPC, Multi-Party Computation, Privacy-Preserving Computation, Güvenli Çok Taraflı Hesaplama
関連	3	3	3
概要	Homomorphic Encryption (HE) is a cryptographic framework that allows arbitrary computations to be performed directly on encrypted data without requiring decryption. First realized as a fully general construction by Craig Gentry in 2009 using ideal lattices, it enables a server to process sensitive data and return an encrypted result that, when decrypted by the data owner, equals the result of performing the same computation on the plaintext. It is foundational to privacy-preserving machine learning, secure cloud computing, and confidential analytics.	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.	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.