A randomized block policy gradient algorithm with differential privacy in Content Centric Networks

2021 ◽  
Vol 17 (12) ◽  
pp. 155014772110599
Author(s):  
Lin Wang ◽  
Xingang Xu ◽  
Xuhui Zhao ◽  
Baozhu Li ◽  
Ruijuan Zheng ◽  
...  
Keyword(s):  
Privacy Protection ◽  
Differential Privacy ◽  
Effective Means ◽  
High Dimensional Data ◽  
Computational Cost ◽  
Gradient Methods ◽  
Multimedia Data ◽  
Gradient Algorithm ◽  
High Dimensional ◽  
Policy Gradient

Policy gradient methods are effective means to solve the problems of mobile multimedia data transmission in Content Centric Networks. Current policy gradient algorithms impose high computational cost in processing high-dimensional data. Meanwhile, the issue of privacy disclosure has not been taken into account. However, privacy protection is important in data training. Therefore, we propose a randomized block policy gradient algorithm with differential privacy. In order to reduce computational complexity when processing high-dimensional data, we randomly select a block coordinate to update the gradients at each round. To solve the privacy protection problem, we add a differential privacy protection mechanism to the algorithm, and we prove that it preserves the [Formula: see text]-privacy level. We conduct extensive simulations in four environments, which are CartPole, Walker, HalfCheetah, and Hopper. Compared with the methods such as important-sampling momentum-based policy gradient, Hessian-Aided momentum-based policy gradient, REINFORCE, the experimental results of our algorithm show a faster convergence rate than others in the same environment.

scholarly journals Local Differential Privacy Protection of High-Dimensional Perceptual Data by the Refined Bayes Network

Sensors ◽  
2020 ◽  
Vol 20 (9) ◽  
pp. 2516
Author(s):  
Chunhua Ju ◽  
Qiuyang Gu ◽  
Gongxing Wu ◽  
Shuangzhu Zhang
Keyword(s):  
Privacy Protection ◽  
Data Privacy ◽  
Differential Privacy ◽  
High Dimensional Data ◽  
Statistical Characteristics ◽  
High Dimensional ◽  
Bayes Network ◽  
Crowd Sensing ◽  
Original Dataset ◽  
Perception System

Although the Crowd-Sensing perception system brings great data value to people through the release and analysis of high-dimensional perception data, it causes great hidden danger to the privacy of participants in the meantime. Currently, various privacy protection methods based on differential privacy have been proposed, but most of them cannot simultaneously solve the complex attribute association problem between high-dimensional perception data and the privacy threat problems from untrustworthy servers. To address this problem, we put forward a local privacy protection based on Bayes network for high-dimensional perceptual data in this paper. This mechanism realizes the local data protection of the users at the very beginning, eliminates the possibility of other parties directly accessing the user’s original data, and fundamentally protects the user’s data privacy. During this process, after receiving the data of the user’s local privacy protection, the perception server recognizes the dimensional correlation of the high-dimensional data based on the Bayes network, divides the high-dimensional data attribute set into multiple relatively independent low-dimensional attribute sets, and then sequentially synthesizes the new dataset. It can effectively retain the attribute dimension correlation of the original perception data, and ensure that the synthetic dataset and the original dataset have as similar statistical characteristics as possible. To verify its effectiveness, we conduct a multitude of simulation experiments. Results have shown that the synthetic data of this mechanism under the effective local privacy protection has relatively high data utility.

scholarly journals PPDP-PCAO: An Efficient High-Dimensional Data Releasing Method With Differential Privacy Protection

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 176429-176437 ◽  
Author(s):  
Wanjie Li ◽  
Xing Zhang ◽  
Xiaohui Li ◽  
Guanghui Cao ◽  
Qingyun Zhang
Keyword(s):  
Privacy Protection ◽  
Differential Privacy ◽  
High Dimensional Data ◽  
High Dimensional

scholarly journals The Discrete Gaussian Expectation Maximization (Gradient) Algorithm for Differential Privacy

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Weisan Wu
Keyword(s):  
Em Algorithm ◽  
Expectation Maximization ◽  
Differential Privacy ◽  
High Dimensional Data ◽  
Gradient Algorithm ◽  
High Dimensional ◽  
Sensitive Data ◽  
The Difference

In this paper, we give a modified gradient EM algorithm; it can protect the privacy of sensitive data by adding discrete Gaussian mechanism noise. Specifically, it makes the high-dimensional data easier to process mainly by scaling, truncating, noise multiplication, and smoothing steps on the data. Since the variance of discrete Gaussian is smaller than that of the continuous Gaussian, the difference privacy of data can be guaranteed more effectively by adding the noise of the discrete Gaussian mechanism. Finally, the standard gradient EM algorithm, clipped algorithm, and our algorithm (DG-EM) are compared with the GMM model. The experiments show that our algorithm can effectively protect high-dimensional sensitive data.

Multi-Party High-Dimensional Data Publishing Under Differential Privacy

2020 ◽  
Vol 32 (8) ◽  
pp. 1557-1571 ◽  
Author(s):  
Xiang Cheng ◽  
Peng Tang ◽  
Sen Su ◽  
Rui Chen ◽  
Zequn Wu ◽  
...  
Keyword(s):  
Differential Privacy ◽  
High Dimensional Data ◽  
Data Publishing ◽  
High Dimensional

scholarly journals An Improved Integrated Hash and Attributed based Encryption Model on High Dimensional Data in Cloud Environment

2017 ◽  
Vol 7 (2) ◽  
pp. 950
Author(s):  
Satheesh K S V A Kavuri ◽  
Gangadhara Rao Kancherla ◽  
Basaveswararao Bobba
Keyword(s):  
Privacy Protection ◽  
High Dimensional Data ◽  
Data Access ◽  
Computational Time ◽  
High Dimensional ◽  
Access Methods ◽  
Protection Mechanism ◽  
Cloud Data ◽  
High Data ◽  
Storage Format

Cloud computing is a distributed architecture where user can store their private, public or any application software components on it. Many cloud based privacy protection solutions have been implemented, however most of them only focus on limited data resources and storage format. Data confidentiality and inefficient data access methods are the major issues which block the cloud users to store their high dimensional data. With more and more cloud based applications are being available and stored on various cloud servers, a novel multi-user based privacy protection mechanism need to design and develop to improve the privacy protection on high dimensional data. In this paper, a novel integrity algorithm with attribute based encryption model was implemented to ensure confidentiality for high dimensional data security on cloud storage. The main objective of this model is to store, transmit and retrieve the high dimensional cloud data with low computational time and high security. Experimental results show that the proposed model has high data scalability, less computational time and low memory usage compared to traditional cloud based privacy protection models.

scholarly journals A Non-Reversible Privacy Preservation Model for Outsourced High-Dimensional Healthcare Data

2021 ◽  
Author(s):  
Syed Usama Khalid Bukhari ◽  
Anum Qureshi ◽  
Adeel Anjum ◽  
Munam Ali Shah
Keyword(s):  
Privacy Preservation ◽  
Differential Privacy ◽  
Personal Information ◽  
High Dimensional Data ◽  
High Dimensional ◽  
Sensitive Data ◽  
Privacy Concerns ◽  
Healthcare Data ◽  
Pros And Cons ◽  
Privacy Breaches

<div> <div> <div> <p>Privacy preservation of high-dimensional healthcare data is an emerging problem. Privacy breaches are becoming more common than before and affecting thousands of people. Every individual has sensitive and personal information which needs protection and security. Uploading and storing data directly to the cloud without taking any precautions can lead to serious privacy breaches. It’s a serious struggle to publish a large amount of sensitive data while minimizing privacy concerns. This leads us to make crucial decisions for the privacy of outsourced high-dimensional healthcare data. Many types of privacy preservation techniques have been presented to secure high-dimensional data while keeping its utility and privacy at the same time but every technique has its pros and cons. In this paper, a novel privacy preservation NRPP model for high-dimensional data is proposed. The model uses a privacy-preserving generative technique for releasing sensitive data, which is deferentially private. The contribution of this paper is twofold. First, a state-of-the-art anonymization model for high-dimensional healthcare data is proposed using a generative technique. Second, achieved privacy is evaluated using the concept of differential privacy. The experiment shows that the proposed model performs better in terms of utility. </p> </div> </div> </div>

scholarly journals A Non-Reversible Privacy Preservation Model for Outsourced High-Dimensional Healthcare Data

2021 ◽  
Author(s):  
Syed Usama Khalid Bukhari ◽  
Anum Qureshi ◽  
Adeel Anjum ◽  
Munam Ali Shah
Keyword(s):  
Privacy Preservation ◽  
Differential Privacy ◽  
Personal Information ◽  
High Dimensional Data ◽  
High Dimensional ◽  
Sensitive Data ◽  
Privacy Concerns ◽  
Healthcare Data ◽  
Pros And Cons ◽  
Privacy Breaches

<div> <div> <div> <p>Privacy preservation of high-dimensional healthcare data is an emerging problem. Privacy breaches are becoming more common than before and affecting thousands of people. Every individual has sensitive and personal information which needs protection and security. Uploading and storing data directly to the cloud without taking any precautions can lead to serious privacy breaches. It’s a serious struggle to publish a large amount of sensitive data while minimizing privacy concerns. This leads us to make crucial decisions for the privacy of outsourced high-dimensional healthcare data. Many types of privacy preservation techniques have been presented to secure high-dimensional data while keeping its utility and privacy at the same time but every technique has its pros and cons. In this paper, a novel privacy preservation NRPP model for high-dimensional data is proposed. The model uses a privacy-preserving generative technique for releasing sensitive data, which is deferentially private. The contribution of this paper is twofold. First, a state-of-the-art anonymization model for high-dimensional healthcare data is proposed using a generative technique. Second, achieved privacy is evaluated using the concept of differential privacy. The experiment shows that the proposed model performs better in terms of utility. </p> </div> </div> </div>

scholarly journals Perbandingan Koefisien NMF dan Proyeksi Bilinear Space Sebagai Fitur pada Pengenalan Ekspresi Wajah Manusia

2012 ◽  
Vol 3 (1) ◽  
pp. 702
Author(s):  
William Salim
Keyword(s):  
High Dimensional Data ◽  
Face Image ◽  
Multimedia Data ◽  
High Dimensional ◽  
Human Face ◽  
Negative Data ◽  
Time Efficiency ◽  
Face Expression ◽  
Classification Technique ◽  
Space Projection

NMF is one new developed method to make the part-based representation of non-negative data, such as human face image. NMF can reduce the dimension of high dimensional data such as multimedia data. In many researches,NMF can also used as a classification technique done by utilizing the extracted feature through NMF process. This article discusses about the classification technique of human face expression using NMF. This is done using NMF coeffisient and bilinear projection of face image. Some researches show the use of NMF coefficient in classification and some others use bilinear space projection. This research is conducted by simulating face espression recognition to the two available approaches and then comparing the accuracy and time efficiency aspect of the two methods. Through this research, it can be concluded that the use of NMF coefficient results in better accuracy compared to bilinear space projection, but bilinear space projection obtains better time efficiency.

scholarly journals Deep learning-based clustering approaches for bioinformatics

2020 ◽  
Author(s):  
Md Rezaul Karim ◽  
Oya Beyan ◽  
Achille Zappa ◽  
Ivan G Costa ◽  
Dietrich Rebholz-Schuhmann ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cancer Genomics ◽  
Clustering Algorithms ◽  
Effective Means ◽  
High Dimensional Data ◽  
Computational Method ◽  
High Dimensional ◽  
Gene Expressions ◽  
Starting Point ◽  
Clustering Quality

Abstract Clustering is central to many data-driven bioinformatics research and serves a powerful computational method. In particular, clustering helps at analyzing unstructured and high-dimensional data in the form of sequences, expressions, texts and images. Further, clustering is used to gain insights into biological processes in the genomics level, e.g. clustering of gene expressions provides insights on the natural structure inherent in the data, understanding gene functions, cellular processes, subtypes of cells and understanding gene regulations. Subsequently, clustering approaches, including hierarchical, centroid-based, distribution-based, density-based and self-organizing maps, have long been studied and used in classical machine learning settings. In contrast, deep learning (DL)-based representation and feature learning for clustering have not been reviewed and employed extensively. Since the quality of clustering is not only dependent on the distribution of data points but also on the learned representation, deep neural networks can be effective means to transform mappings from a high-dimensional data space into a lower-dimensional feature space, leading to improved clustering results. In this paper, we review state-of-the-art DL-based approaches for cluster analysis that are based on representation learning, which we hope to be useful, particularly for bioinformatics research. Further, we explore in detail the training procedures of DL-based clustering algorithms, point out different clustering quality metrics and evaluate several DL-based approaches on three bioinformatics use cases, including bioimaging, cancer genomics and biomedical text mining. We believe this review and the evaluation results will provide valuable insights and serve a starting point for researchers wanting to apply DL-based unsupervised methods to solve emerging bioinformatics research problems.

scholarly journals Differentially Private Actor and Its Eligibility Trace

Electronics ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. 1486
Author(s):  
Kanghyeon Seo ◽  
Jihoon Yang
Keyword(s):  
Real World ◽  
Autonomous Navigation ◽  
Differential Privacy ◽  
Cosine Similarity ◽  
Gradient Algorithm ◽  
Sensitive Data ◽  
Private Actor ◽  
Policy Gradient ◽  
Eligibility Trace ◽  
Real World Problems

We present a differentially private actor and its eligibility trace in an actor-critic approach, wherein an actor takes actions directly interacting with an environment; however, the critic estimates only the state values that are obtained through bootstrapping. In other words, the actor reflects the more detailed information about the sequence of taken actions on its parameter than the critic. Moreover, their corresponding eligibility traces have the same properties. Therefore, it is necessary to preserve the privacy of an actor and its eligibility trace while training on private or sensitive data. In this paper, we confirm the applicability of differential privacy methods to the actors updated using the policy gradient algorithm and discuss the advantages of such an approach with regard to differentially private critic learning. In addition, we measured the cosine similarity between the differentially private applied eligibility trace and the non-differentially private eligibility trace to analyze whether their anonymity is appropriately protected in the differentially private actor or the critic. We conducted the experiments considering two synthetic examples imitating real-world problems in medical and autonomous navigation domains, and the results confirmed the feasibility of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document