Differentially private regression analysis with dynamic privacy allocation

Pan, Ke; Gong, Maoguo; Feng, Kaiyuan; Wang, Kun

doi:10.1016/j.knosys.2021.106795

Cited by 11 publications

(4 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These findings underscore the effectiveness of Gaussian process-based differential privacy mechanisms in safeguarding data privacy while maintaining usability [19]. Practically, this suggests that adjusting differential privacy algorithm parameters can optimize the balance between privacy protection and data usability, maximizing data value retention while securing user privacy.…”

Section: Effectiveness Of Differential Privacy Protectionmentioning

confidence: 74%

Intelligent Scene-Adaptive Desensitization: A Machine Learning Approach for Dynamic Data Privacy in Virtual Power Plants

Yang,

Gao,

et al. 2024

Electronics

View full text Add to dashboard Cite

In the context of virtual power plants (VPPs), the one-size-fits-all approach of traditional static desensitization methods proves inadequate due to the diverse and dynamic operational scenarios encountered. These methods fail to provide the necessary flexibility for varying data privacy requirements across different scenarios. To address this shortcoming, our research introduces a dynamic desensitization method specifically designed for VPPs. Leveraging machine learning for adaptive scene recognition, the method adjusts data privacy levels intelligently according to each unique scenario. A novel similarity utility function and a Gaussian processes-based differential privacy algorithm ensure tailored and efficient privacy protection. Experimental results highlight an 87.5% accuracy in scene recognition, validating our method’s capability to adapt to diverse scenarios effectively. This study contributes to the field by providing a nuanced approach to data protection, effectively addressing the specific needs of complex VPP environments.

show abstract

Section: Effectiveness Of Differential Privacy Protectionmentioning

confidence: 74%

Intelligent Scene-Adaptive Desensitization: A Machine Learning Approach for Dynamic Data Privacy in Virtual Power Plants

Yang,

Gao,

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…These works apply DP during the training to produce PP models. Pan et al [66] present adaptive differentially private regression (ADPR) mechanism, a dynamic privacy noise allocation mechanism that takes into account the relevance of the input attributes to the outputs. The mechanism consists of adding Laplace noise drawn from Lap( ∆ f ϵj ) into the polynomial coefficients of the objective function.…”

Section: Laplace and Gaussianmentioning

confidence: 99%

“…Although this approach gives better accuracy compared to [67]- [69], [83], it is costly in terms of computation as it has to run a pre-processing learning step to determine the relevance of each attribute. The approaches of [66] and [67] are the same, except that [67] adds noise with the same privacy budget which may decrease the model's accuracy.…”

Section: Laplace and Gaussianmentioning

confidence: 99%

See 1 more Smart Citation

Differential Privacy for Deep and Federated Learning: A Survey

2022

View full text Add to dashboard Cite

Users' privacy is vulnerable at all stages of the deep learning process. Sensitive information of users may be disclosed during data collection, or during training, or even after releasing the trained learning model. Differential privacy (DP) is one of the main approaches proven to ensure strong privacy protection in data analysis. DP protects the users' privacy by adding noise to the original dataset or the learning parameters. Thus, an attacker could not retrieve the sensitive information of an individual involved in the training dataset. In this survey paper, we analyze and present the main ideas based on DP to guarantee users' privacy in deep and federated learning. In addition, we illustrate all types of probability distributions that satisfy the DP mechanism, with their properties and use cases. Furthermore, we bridge the gap in the literature by providing a comprehensive overview of the different variants of DP, highlighting their advantages and limitations. Our study reveals the gap between theory and application, accuracy, and robustness of DP. Finally, we provide several open problems and future research directions.

show abstract