השוואת שיטות

	פרטיות דיפרנציאלית	זיקוק ידע (Knowledge Distillation)
תחום	פרטיות	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2006	2015
הוגה השיטה	Cynthia Dwork	Hinton, G., Vinyals, O. & Dean, J.
סוג	Privacy-preserving randomized mechanism	Neural network compression (teacher–student)
מקור מכונן	Dwork, C. (2006). Differential privacy. International Colloquium on Automata, Languages and Programming (ICALP), 1–12.	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.
כינויים	DP, epsilon-differential privacy, randomized privacy, Diferansiyel Gizlilik	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation
קשורות	3	5
תקציר	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.	Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster.