Privacy Protection Technology Based on Machine Learning and Intelligent Data Recognition

liu, Qiang

doi:10.1155/2022/1598826

Cited by 5 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditionally, convolutions are employed in image analysis to blur as well as sharpen pictures, but they can also be used for other tasks. CNNs impose a connection oriented pattern among neurons of adjacent layers (for instance, by embossing and enhancing edges) [20].The 2D convolution layer, which is frequently referred to by the acronym conv2D, is the most widely used type of convolution. In a conv2D layer, an elementwise multiplication is carried out by a filter or kernel as it "slides" over the 2D input data.…”

Section: D Convolutional Neural Networkmentioning

confidence: 99%

Differential Privacy Preserving Using TensorFlow DP-SGD and 2D-CNN for Large-Scale Image Data

Rajput¹,

Tiwari²

2023

IJRASET

View full text Add to dashboard Cite

Although smart wearables have many potential advantages, their widespread and ongoing use raises a number of privacy issues and difficult information security challenges. This article, present a thorough analysis of current wearable sensorbased big data analytics applications that protect user privacy. We draw attention to the fundamental aspects of privacy and security for applications on wearable technology. Then, we look at how deep learning techniques like 2D CNN are used for better evaluation and privacy preservation as well as for differential privacy of Tensor flow. DP-SGD (Differentially private stochastic gradient descent)The metrics are epsilon as well as accuracy, with 0.56 epsilon and 85.17% accuracy for three epochs and 100.09 epsilon and 95.28 accuracies for twenty epochs, respectively. Model training Accuracy is 94.71%. Also, present a case study on privacy-preserving machine learning techniques. Herein, we theoretically and empirically evaluate the privacypreserving deep learning framework's performance. We explain the implementation details of a case study of a secure prediction service using the 2D convolutional neural network (2D CNN) model

show abstract

Section: D Convolutional Neural Networkmentioning

confidence: 99%

Differential Privacy Preserving Using TensorFlow DP-SGD and 2D-CNN for Large-Scale Image Data

Rajput¹,

Tiwari²

2023

IJRASET

View full text Add to dashboard Cite

show abstract

“…Encryption, access limits, and anonymization methods are just some of the security measures that schools should put in place to secure students' personal information. The Family Educational Rights and Privacy Act (FERPA) in the United States regulate the use and disclosure of student data, and shall be followed [8][9][10][11][12].…”

Section: Machine Learning In Data Privacymentioning

confidence: 99%

“…Finally, the gradient value from the stochastic gradient descent technique is used to adjust the level of the Gaussian noise and protect the sensitive data. The experimental findings showed that a middle ground could be found between the availability and privacy protection of the training data set by modifying the parameters of the depth differential privacy model based on variations in private information in the data [10]. 2023) predicted student retention using app-based engagement metrics and socio-demographic factors with machine learning.…”

Section: B Holicza Et Al (mentioning

confidence: 99%

Comprehensive analysis of factors influencing the real-world application of machine learning for student success rate calculation and their impacts on student achievement & educational institutions

Divvyam Arora

2023

World J. Adv. Res. Rev.

View full text Add to dashboard Cite

The successful application of machine learning for student success rate calculation is contingent upon a comprehensive analysis of several interrelated factors that span the educational landscape. Educational institutions must ensure that they have access to accurate and relevant data, including student demographics, academic performance records, and even extracurricular activities, to build effective predictive models. Moreover, data privacy and security concerns must be addressed to maintain the integrity of sensitive student information. Next, the choice of machine learning algorithms is crucial. The selection should align with the specific objectives of predicting student success, taking into account the type and volume of data available. Factors such as classification algorithms, regression techniques, and deep learning models must be carefully considered, and their performance must be assessed through rigorous testing and validation. Addressing potential biases in machine learning models is crucial to ensure equitable outcomes. Careful attention must be paid to the training data, as biased data can lead to discriminatory predictions. Ongoing monitoring and model refinement are necessary to minimize these biases and promote fairness in student success predictions. Thus present paper is focused on a comprehensive analysis of factors influencing the real-world application of machine learning for student success rate. In order to achieve this goal, relevant researches on machine learning is considered and further enhancement has been made to make the proposed work more efficient.

show abstract

“…Smart home privacy no longer stays in traditional privacy information such as name, ID number, bank card number, password, and family address. Interests, habits, behavior, and other information are becoming more and more common [43]. Once this data is abused or spread, it brings excellent instability to the society and even affects the country's security.…”

Section: Privacy Awarenessmentioning

confidence: 99%

The Development of Privacy Protection Standards for Smart Home

Liu¹,

Yang

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the rapid development of network technology, society has entered the Internet of Things (IoT) era. Enriching IoT devices enable smart home privacy information to be easily obtained through data mining. Smart home privacy protection (SHPP) has a farreaching impact on the development of all aspects of society. Industrial and academic circles pay great attention to the privacy protection of the smart home, and the ability to protect the privacy needs to be improved. SHPP standards are one way to evaluate privacy protection capabilities at this stage. Based on our research on privacy protection standards, this paper summarizes the development of privacy protection standards for the first time. It divides them into three phases: creation, exploration, and expansion. According to the characteristics of the privacy data rotation, the SHPP standard system is proposed, including basic commonality, critical technology, auxiliary management, test and certification, and device application. Finally, we focus on the opportunity and challenges of smart home privacy security standards brought by the current big data and prospect the trend of privacy protection technologies and standard study. They provide a connection for subsequent standard investigations.

show abstract

Privacy Protection Technology Based on Machine Learning and Intelligent Data Recognition

Cited by 5 publications

References 19 publications

Differential Privacy Preserving Using TensorFlow DP-SGD and 2D-CNN for Large-Scale Image Data

Differential Privacy Preserving Using TensorFlow DP-SGD and 2D-CNN for Large-Scale Image Data

Comprehensive analysis of factors influencing the real-world application of machine learning for student success rate calculation and their impacts on student achievement & educational institutions

The Development of Privacy Protection Standards for Smart Home

Contact Info

Product

Resources

About