Please use this identifier to cite or link to this item:
https://doi.org/10.1145/3343031.3350963
Title: | Human-imperceptible Privacy Protection Against Machines | Authors: | SHEN ZHIQI FAN SHAOJING Wong Yong Kang KANKANHALLI MOHAN S |
Keywords: | Privacy protection Social multimedia Deep neural network |
Issue Date: | 20-Oct-2019 | Publisher: | Association for Computing Machinery, New York, NY, United States | Citation: | SHEN ZHIQI, FAN SHAOJING, Wong Yong Kang, KANKANHALLI MOHAN S (2019-10-20). Human-imperceptible Privacy Protection Against Machines. MM 2019 - Proceedings of the 27th ACM International Conference on Multimedia : 1119-1128. ScholarBank@NUS Repository. https://doi.org/10.1145/3343031.3350963 | Abstract: | Privacy concerns with social media have recently been under the spotlight, due to a few incidents on user data leakage on social networking platforms. With the current advances in machine learning and big data, computer algorithms often act as a first-step filter for privacy breaches, by automatically selecting content with sensitive information, such as photos that contain faces or vehicle license plate. In this paper we propose a novel algorithm to protect the sensitive attributes against machines, meanwhile keeping the changes imperceptible to humans. In particular, we first conducted a series of human studies to investigate multiple factors that influence human sensitivity to the visual changes. We discover that human sensitivity is influenced by multiple factors, from low-level features such as illumination, texture, to high-level attributes like object sentiment and semantics. Based on our human data, we propose for the first time the concept of human sensitivity map. With the sensitivity map, we design a human-sensitivity-aware image perturbation model, which is able to modify the computational classification results of sensitive attributes while preserving the remaining attributes. Experiments on real world data demonstrate the superior performance of the proposed model on human-imperceptible privacy protection. | Source Title: | MM 2019 - Proceedings of the 27th ACM International Conference on Multimedia | URI: | https://scholarbank.nus.edu.sg/handle/10635/168537 | ISBN: | 9781450368896 | DOI: | 10.1145/3343031.3350963 |
Appears in Collections: | Staff Publications Elements Students Publications |
Show full item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
ZhiqiACMMM2019-camera ready-v6.pdf | 55.63 MB | Adobe PDF | OPEN | Published | View/Download |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.