| Title | Differential Privacy Online Learning Based on the Composition Theorem |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Jiang, P., Liao, S. |
| Conference Name | 2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC) |
| Date Published | jul |
| Keywords | composability, composition theorem, Differential privacy, Gaussian noise, Human Behavior, Learning systems, online learning, Prediction algorithms, privacy, Programming, pubcrawl, Resiliency, Scalability, sublinear regret |
| Abstract | Privacy 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 (, d)-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. |
| DOI | 10.1109/ICEIEC49280.2020.9152303 |
| Citation Key | jiang_differential_2020 |
Differential Privacy Online Learning Based on the Composition Theorem