Adversaries or allies? Privacy and deep learning in big data era

Abstract

Summary Deep learning methods have become the basis of new AI‐based services on the Internet in big data era because of their unprecedented accuracy. Meanwhile, it raises obvious privacy issues. The deep learning–assisted privacy attack can extract sensitive personal information not only from the text but also from unstructured data such as images and videos. In this paper, we proposed a framework to protect image privacy against deep learning tools, along with two new metrics that measure image privacy. Moreover, we propose two different image privacy protection schemes based on the two metrics, utilizing the adversarial example idea. The performance of our solution is validated by simulations on two different datasets. Our research shows that we can protect the image privacy by adding a small amount of noise that has a humanly imperceptible impact on the image quality, especially for images of complex structures and textures.

On Safeguarding Privacy and Security in the Framework of Federated Learning

“…In particular, the emergence of centralized searchable data repositories has made the leakage of private information, e.g. health conditions, travel information, and financial data, an urgent social problem [2]. Furthermore, the diverse set of open data applications, such as census data dissemination and social networks, place more emphasis on privacy concerns.…”

Privacy preservation for image data: A GAN‐based method

“…Mirjalili et al 14 method involves adding adversarial noise to the original image so that the fake image misleads deep neural network models into incorrect classifications. 16 And most recently, Liu et al 17 summarize the image privacy and related methods in a survey.…”

Editorial: Recent advances in machine learning for cybersecurity

“…However, such efforts often become a patch‐after‐attack practice due to the inabilities of dealing with new attacks. To address this challenge, Liu et al propose a novel framework for the image privacy protection. Liu et al's framework also includes two new metrics for measuring image privacy.…”