قارن الطرق

	التشفير المتجانس	الخصوصية التفاضلية
المجال	الخصوصية	الخصوصية
العائلة	Machine learning	Machine learning
سنة النشأة	2009	2006
صاحب الطريقة	Craig Gentry	Cynthia Dwork
النوع	Lattice-based cryptographic scheme	Privacy-preserving randomized mechanism
المصدر التأسيسي	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.
الأسماء البديلة	FHE, Fully Homomorphic Encryption, Leveled Homomorphic Encryption, Homomorfik Şifreleme	DP, epsilon-differential privacy, randomized privacy, Diferansiyel Gizlilik
ذات صلة	3	3
الملخص	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.