How Long to Read Towards Ethical and Robust Privacy-preserving Machine Learning

How Long Does it Take to Read Towards Ethical and Robust Privacy-preserving Machine Learning?

It takes the average reader to read Towards Ethical and Robust Privacy-preserving Machine Learning by Hui Hu

Assuming a reading speed of 250 words per minute. Learn more

Description

Privacy in machine learning has received tremendous attention in recent years, which mainly involves data privacy and model privacy. Recent studies have revealed numerous privacy attacks and privacy-preserving methodologies, that vary across a broad range of applications. To date, however, there exist few powerful methodologies in addressing privacy-preserving challenges in ethical machine learning and deep learning due to the difficulty of guaranteeing model robustness and privacy-preserving simultaneously. In this dissertation, two critical problems will be investigated and addressed: data privacy-preserving in ethical machine learning, and model privacy-preserving in deep learning under powerful side-channel power attacks. First, we investigate the problem of data privacy-preserving in ethical machine learning with the following two considerations: (1) Users’ privacy (i.e., race, religion, gender, etc.) is severely leaked in ethical machine learning as most existing techniques require full access to sensitive personal data to achieve model fairness. To address this pressing privacy issue, we propose a distributed privacy-preserving fair machine learning mechanism based on random projection theory and multi-party computation. Through rigorous theoretical analysis and comprehensive simulations, we can prove that the proposed mechanism is efficient for privacy-preserving while guaranteeing good model robustness. Further, (2) considering the dependency relation of graph data in ethical machine learning, an individual’s privacy can be leaked due to the sensitive information disclosure of their neighbors. Typically, in a graph neural network, the sensitive information disclosure of non-private users potentially exposes the sensitive information of private users in the same graph owing to the homophily property and message-passing mechanism of graph neural networks. To address this problem, based on disentangled representation learning, we propose a principled privacy-preserving graph neural network model to mitigate individual privacy leakage of private users in a graph, which maintains competitive model accuracy compared with non-private graph neural networks. We verify the effectiveness of the proposed privacy-preserving model through extensive experiments and theoretical analysis. Second, as the disclosure of model privacy can allow adversaries to potentially infer users’ extremely sensitive decisions, further, we study model privacy-preserving in deep learning under side-channel power attacks. Side-channel power attacks are powerful attacks that infer the internal information of a traditional deep neural network (i.e., model privacy), which can be leveraged to infer some important decisions of users. Therefore, with the increasing applications of deep learning, training privacy-preserving deep neural networks under side-channel power attacks is a pressing task. This dissertation proposes an efficient solution for training privacy-preserving deep neural networks to resist powerful side-channel power attacks, which randomly trains multiple independent sub-networks to generate random power traces in the temporal domain. The comprehensive theoretical analysis and experimental results demonstrate the effectiveness of the proposed approach in model privacy-preserving and model robustness under side-channel power attacks.

How long is Towards Ethical and Robust Privacy-preserving Machine Learning?

Towards Ethical and Robust Privacy-preserving Machine Learning by Hui Hu is 0 pages long, and a total of 0 words.

This makes it 0% the length of the average book. It also has 0% more words than the average book.

How Long Does it Take to Read Towards Ethical and Robust Privacy-preserving Machine Learning Aloud?

The average oral reading speed is 183 words per minute. This means it takes to read Towards Ethical and Robust Privacy-preserving Machine Learning aloud.

What Reading Level is Towards Ethical and Robust Privacy-preserving Machine Learning?

Towards Ethical and Robust Privacy-preserving Machine Learning is suitable for students ages 2 and up.

Note that there may be other factors that effect this rating besides length that are not factored in on this page. This may include things like complex language or sensitive topics not suitable for students of certain ages.

When deciding what to show young students always use your best judgement and consult a professional.

Where Can I Buy Towards Ethical and Robust Privacy-preserving Machine Learning?

Towards Ethical and Robust Privacy-preserving Machine Learning by Hui Hu is sold by several retailers and bookshops. However, Read Time works with Amazon to provide an easier way to purchase books.

To buy Towards Ethical and Robust Privacy-preserving Machine Learning by Hui Hu on Amazon click the button below.