RoD: Evaluating the Risk of Data Disclosure Using Noise Estimation for Differential Privacy

Tsou, Yao-Tung; Chen, Hung-Li; Chen, Jiayang

doi:10.1109/tbdata.2019.2916108

Cited by 8 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chorus has been released as open-source for protecting individual privacy [12]. However, the DP-based PPDL models result in reducing the object classification accuracy because the large amount of added noise eventually distorts the data [27].…”

Section: Related Workmentioning

confidence: 99%

Structural Image De-Identification for Privacy-Preserving Deep Learning

Choi

Shin

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Due to the risk of data leakage while training deep learning models in a shared environment, we propose a new privacy-preserving deep learning(PPDL) method using a structural image deidentification approach for object classification. The proposed structural image de-identification approach is designed based on the fact that the degree of structural distortion of an image object has the greatest impact on human's perceptual system. Thus, by modifying only the structural parts of the original one using order preserving encryption(OPE), the proposed structural image de-identification approach decreases only the recognition rate by human. From the experimental results using different standard datasets, we show that the object classification accuracy of the proposed structural image de-identification method is almost the same as the deep learning performance for non-encrypted images, without revealing the original image contents including sensitive information. Also, by handling the trade-off between object classification accuracy and privacy protection for the de-identified image, we experimentally find the optimal size of input image for the proposed structural image de-identification approach.

show abstract

Section: Related Workmentioning

confidence: 99%

Structural Image De-Identification for Privacy-Preserving Deep Learning

Choi

Shin

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Du and Wang [13] proposed a query model and implemented differential privacy by Laplace noise. Tsou and Chen [17] quantified the disclosure risk and linked the differential privacy with k-anonymity. Zhang and Liu [18] proposed a privacy-preserving decision tree classification model based on differential privacy mechanism, through the Laplace mechanism and index mechanism, which provided users with a secure data access interface and optimized the search scheme to reduce the error rate.…”

Section: Research On the Basicmentioning

confidence: 99%

Research on Selection Method of Privacy Parameter $ε$

Sun

2020

Security and Communication Networks

View full text Add to dashboard Cite

Budget factor is an important factor to measure the intensity of differential privacy, and its allocation scheme has a great impact on privacy protection. This paper studies the selection of the parameter ε in several cases of differential privacy. Firstly, this paper proposes a differential privacy protection parameter configuration method based on fault tolerance interval and analyzes the adversaryʼs fault tolerance under different noise distribution location parameters and scale parameters. Secondly, this paper proposes an algorithm to optimize the application scenarios of multiquery, studies the location parameters and scale parameters in detail, and proposes a differential privacy mechanism to solve the multiuser query scenarios. Thirdly, this paper proposes the differential privacy parameter selection methods based on the single attack and repeated attacks and calculates the upper bound of the parameter ε based on the sensitivity Δ q , the length of the fault tolerance interval L , and the success probability p as long as the fault tolerance interval. Finally, we have carried out a variety of simulation experiments to verify our research scheme and give the corresponding analysis results.

show abstract

Beyond Data Collection: Safeguarding User Privacy in Social Robotics

Dorafshanian,

Aitsam,

Mejri

et al. 2024

2024 IEEE International Conference on Industrial Technology (ICIT)

View full text Add to dashboard Cite

RoD: Evaluating the Risk of Data Disclosure Using Noise Estimation for Differential Privacy

Cited by 8 publications

References 21 publications

Structural Image De-Identification for Privacy-Preserving Deep Learning

Structural Image De-Identification for Privacy-Preserving Deep Learning

Research on Selection Method of Privacy Parameter $ε$

Beyond Data Collection: Safeguarding User Privacy in Social Robotics

Contact Info

Product

Resources

About

RoD: Evaluating the Risk of Data Disclosure Using Noise Estimation for Differential Privacy

Cited by 8 publications

References 21 publications

Structural Image De-Identification for Privacy-Preserving Deep Learning

Structural Image De-Identification for Privacy-Preserving Deep Learning

Research on Selection Method of Privacy Parameter ε

Beyond Data Collection: Safeguarding User Privacy in Social Robotics

Contact Info

Product

Resources

About

Research on Selection Method of Privacy Parameter $ε$