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

By Bo Liu, Ming Ding, Tianqing Zhu, Yang Xiang, Wanlei Zhou. 2018

27 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. H. Vincent Poor
2. Ming Ding
3. Chuan Ma
4. Jun Li
5. Farhad Farokhi
6. Tony Q. S. Quek
7. Bo Liu
8. Zihuai Lin

In Computer Vision and Pattern Recognition

1. Jun Li
2. Ming Ding
3. Farhad Farokhi
4. H. Vincent Poor
5. Tony Q. S. Quek
6. Bo Liu
7. Zihuai Lin
8. Wenny Rahayu

Citations in the corpus

• On Safeguarding Privacy and Security in the Framework of Federated Learning (2019, background): “health conditions, travel information, and financial data, an urgent social problem [2].”
• When Machine Learning Meets Privacy (2020, methodology): “rial examples based on the “Faster RCNN framework”. Jia et al. [65] proposed a two-phase framework called AttriGuard to defend against attribute inference attacks launched by a classifier. Liu et al. [80] investigated schemes for using adversarial examples in ML systems so that they cannot identify ”