Visible to the public Differential Privacy Online Learning Based on the Composition Theorem

TitleDifferential Privacy Online Learning Based on the Composition Theorem
Publication TypeConference Paper
Year of Publication2020
AuthorsJiang, P., Liao, S.
Conference Name2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)
Date Publishedjul
Keywordscomposability, composition theorem, Differential privacy, Gaussian noise, Human Behavior, Learning systems, online learning, Prediction algorithms, privacy, Programming, pubcrawl, Resiliency, Scalability, sublinear regret
AbstractPrivacy protection is becoming more and more important in the era of big data. Differential privacy is a rigorous and provable privacy protection method that can protect privacy for a single piece of data. But existing differential privacy online learning methods have great limitations in the scope of application and accuracy. Aiming at this problem, we propose a more general and accurate algorithm, named DPOL-CT, for differential privacy online learning. We first distinguish the difference in differential privacy protection between offline learning and online learning. Then we prove that the DPOL-CT algorithm achieves (∊, δ)-differential privacy for online learning under the Gaussian, the Laplace and the Staircase mechanisms and enjoys a sublinear expected regret bound. We further discuss the trade-off between the differential privacy level and the regret bound. Theoretical analysis and experimental results show that the DPOL-CT algorithm has good performance guarantees.
Citation Keyjiang_differential_2020