A Privacy-Preserving Outsourced Data Model in Cloud Environment
- URL: http://arxiv.org/abs/2211.13542v1
- Date: Thu, 24 Nov 2022 11:27:30 GMT
- Title: A Privacy-Preserving Outsourced Data Model in Cloud Environment
- Authors: Rishabh Gupta and Ashutosh Kumar Singh
- Abstract summary: Data security and privacy problems are among the critical hindrances to using machine learning tools.
A privacy-preserving model is proposed, which protects the privacy of the data without compromising machine learning efficiency.
Fog nodes collect the noise-added data from the data owners, then shift it to the cloud platform for storage, computation, and performing the classification tasks.
- Score: 8.176020822058586
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Nowadays, more and more machine learning applications, such as medical
diagnosis, online fraud detection, email spam filtering, etc., services are
provided by cloud computing. The cloud service provider collects the data from
the various owners to train or classify the machine learning system in the
cloud environment. However, multiple data owners may not entirely rely on the
cloud platform that a third party engages. Therefore, data security and privacy
problems are among the critical hindrances to using machine learning tools,
particularly with multiple data owners. In addition, unauthorized entities can
detect the statistical input data and infer the machine learning model
parameters. Therefore, a privacy-preserving model is proposed, which protects
the privacy of the data without compromising machine learning efficiency. In
order to protect the data of data owners, the epsilon-differential privacy is
used, and fog nodes are used to address the problem of the lower bandwidth and
latency in this proposed scheme. The noise is produced by the
epsilon-differential mechanism, which is then added to the data. Moreover, the
noise is injected at the data owner site to protect the owners data. Fog nodes
collect the noise-added data from the data owners, then shift it to the cloud
platform for storage, computation, and performing the classification tasks
purposes.
Related papers
- FT-PrivacyScore: Personalized Privacy Scoring Service for Machine Learning Participation [4.772368796656325]
In practice, controlled data access remains a mainstream method for protecting data privacy in many industrial and research environments.
We developed the demo prototype FT-PrivacyScore to show that it's possible to efficiently and quantitatively estimate the privacy risk of participating in a model fine-tuning task.
arXiv Detail & Related papers (2024-10-30T02:41:26Z) - Masked Differential Privacy [64.32494202656801]
We propose an effective approach called masked differential privacy (DP), which allows for controlling sensitive regions where differential privacy is applied.
Our method operates selectively on data and allows for defining non-sensitive-temporal regions without DP application or combining differential privacy with other privacy techniques within data samples.
arXiv Detail & Related papers (2024-10-22T15:22:53Z) - K-Nearest Neighbor Classification over Semantically Secure Encrypted Relational Data [0.0]
In public cloud environments while data is encrypted, the cloud service provider typically controls the encryption keys.
This situation makes traditional privacy-preserving classification systems inadequate.
We propose a secure k nearest neighbor classification algorithm for encrypted, outsourced data.
arXiv Detail & Related papers (2024-07-05T19:44:17Z) - Privacy in Cloud Computing through Immersion-based Coding [1.4226399196408985]
We present a framework to design coding mechanisms that allow sharing and processing data in a privacy-preserving manner.
The proposed scheme is built on the synergy of differential privacy and system immersion tools from control theory.
We show that the proposed scheme can be designed to offer any level of differential privacy without degrading the algorithm's utility.
arXiv Detail & Related papers (2024-03-07T13:38:18Z) - Privacy Side Channels in Machine Learning Systems [87.53240071195168]
We introduce privacy side channels: attacks that exploit system-level components to extract private information.
For example, we show that deduplicating training data before applying differentially-private training creates a side-channel that completely invalidates any provable privacy guarantees.
We further show that systems which block language models from regenerating training data can be exploited to exfiltrate private keys contained in the training set.
arXiv Detail & Related papers (2023-09-11T16:49:05Z) - Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining [75.25943383604266]
We question whether the use of large Web-scraped datasets should be viewed as differential-privacy-preserving.
We caution that publicizing these models pretrained on Web data as "private" could lead to harm and erode the public's trust in differential privacy as a meaningful definition of privacy.
We conclude by discussing potential paths forward for the field of private learning, as public pretraining becomes more popular and powerful.
arXiv Detail & Related papers (2022-12-13T10:41:12Z) - A Survey on Differential Privacy with Machine Learning and Future
Outlook [0.0]
differential privacy is used to protect machine learning models from any attacks and vulnerabilities.
This survey paper presents different differentially private machine learning algorithms categorized into two main categories.
arXiv Detail & Related papers (2022-11-19T14:20:53Z) - Certified Data Removal in Sum-Product Networks [78.27542864367821]
Deleting the collected data is often insufficient to guarantee data privacy.
UnlearnSPN is an algorithm that removes the influence of single data points from a trained sum-product network.
arXiv Detail & Related papers (2022-10-04T08:22:37Z) - Mixed Differential Privacy in Computer Vision [133.68363478737058]
AdaMix is an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data.
A few-shot or even zero-shot learning baseline that ignores private data can outperform fine-tuning on a large private dataset.
arXiv Detail & Related papers (2022-03-22T06:15:43Z) - NeuraCrypt: Hiding Private Health Data via Random Neural Networks for
Public Training [64.54200987493573]
We propose NeuraCrypt, a private encoding scheme based on random deep neural networks.
NeuraCrypt encodes raw patient data using a randomly constructed neural network known only to the data-owner.
We show that NeuraCrypt achieves competitive accuracy to non-private baselines on a variety of x-ray tasks.
arXiv Detail & Related papers (2021-06-04T13:42:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.