Protecting Privacy in Shared Photos via Adversarial Examples Based Stealth
Joint Authors
Liu, Yujia
Zhang, Weiming
Yu, Nenghai
Source
Security and Communication Networks
Issue
Vol. 2017, Issue 2017 (31 Dec. 2017), pp.1-15, 15 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2017-11-14
Country of Publication
Egypt
No. of Pages
15
Main Subjects
Information Technology and Computer Science
Abstract EN
Online image sharing in social platforms can lead to undesired privacy disclosure.
For example, some enterprises may detect these large volumes of uploaded images to do users’ in-depth preference analysis for commercial purposes.
And their technology might be today’s most powerful learning model, deep neural network (DNN).
To just elude these automatic DNN detectors without affecting visual quality of human eyes, we design and implement a novel Stealth algorithm, which makes the automatic detector blind to the existence of objects in an image, by crafting a kind of adversarial examples.
It is just like all objects disappear after wearing an “invisible cloak” from the view of the detector.
Then we evaluate the effectiveness of Stealth algorithm through our newly defined measurement, named privacy insurance.
The results indicate that our scheme has considerable success rate to guarantee privacy compared with other methods, such as mosaic, blur, and noise.
Better still, Stealth algorithm has the smallest impact on image visual quality.
Meanwhile, we set a user adjustable parameter called cloak thickness for regulating the perturbation intensity.
Furthermore, we find that the processed images have transferability property; that is, the adversarial images generated for one particular DNN will influence the others as well.
American Psychological Association (APA)
Liu, Yujia& Zhang, Weiming& Yu, Nenghai. 2017. Protecting Privacy in Shared Photos via Adversarial Examples Based Stealth. Security and Communication Networks،Vol. 2017, no. 2017, pp.1-15.
https://search.emarefa.net/detail/BIM-1202779
Modern Language Association (MLA)
Liu, Yujia…[et al.]. Protecting Privacy in Shared Photos via Adversarial Examples Based Stealth. Security and Communication Networks No. 2017 (2017), pp.1-15.
https://search.emarefa.net/detail/BIM-1202779
American Medical Association (AMA)
Liu, Yujia& Zhang, Weiming& Yu, Nenghai. Protecting Privacy in Shared Photos via Adversarial Examples Based Stealth. Security and Communication Networks. 2017. Vol. 2017, no. 2017, pp.1-15.
https://search.emarefa.net/detail/BIM-1202779
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1202779