TY - GEN
T1 - Towards Automated Content-based Photo Privacy Control in User-Centered Social Networks
AU - Vishwamitra, Nishant
AU - Li, Yifang
AU - Hu, Hongxin
AU - Caine, Kelly
AU - Cheng, Long
AU - Zhao, Ziming
AU - Ahn, Gail Joon
N1 - Funding Information:
This work is supported in part by the National Science Foundation (NSF) under the Grant No. 2129164, 2114982, 2031002 and 2120369.
Publisher Copyright:
© 2022 ACM.
PY - 2022/4/14
Y1 - 2022/4/14
N2 - A large number of photos shared online often contain private user information, which can cause serious privacy breaches when viewed by unauthorized users. Thus, there is a need for more efficient privacy control that requires automatic detection of users' private photos. However, the automatic detection of users' private photos is a challenging task, since different users may have different privacy concerns and a generalized one-size-fits-all approach for private photo detection would not be suitable for most users. User-specific detection of private photos should, therefore, be investigated. Furthermore, for effective privacy control, the exact sensitive regions in private photos need to be pinpointed, so that sensitive content can be protected via different privacy control methods. In this paper, we propose a novel system, AutoPri, to enable automatic and user-specific content-based photo privacy control in online social networks. We collect a large dataset of 31, 566 private and public photos from real-world users and present important observations on photo privacy concerns. Our system can automatically detect private photos in a user-specific manner using a detection model based on a multimodal variational autoencoder and pinpoint sensitive regions in private photos with an explainable deep learning-based approach. Our evaluations show that AutoPri can effectively determine user-specific private photos with high accuracy (94.32%) and pinpoint exact sensitive regions in them to enable effective privacy control in user-centered online social networks.
AB - A large number of photos shared online often contain private user information, which can cause serious privacy breaches when viewed by unauthorized users. Thus, there is a need for more efficient privacy control that requires automatic detection of users' private photos. However, the automatic detection of users' private photos is a challenging task, since different users may have different privacy concerns and a generalized one-size-fits-all approach for private photo detection would not be suitable for most users. User-specific detection of private photos should, therefore, be investigated. Furthermore, for effective privacy control, the exact sensitive regions in private photos need to be pinpointed, so that sensitive content can be protected via different privacy control methods. In this paper, we propose a novel system, AutoPri, to enable automatic and user-specific content-based photo privacy control in online social networks. We collect a large dataset of 31, 566 private and public photos from real-world users and present important observations on photo privacy concerns. Our system can automatically detect private photos in a user-specific manner using a detection model based on a multimodal variational autoencoder and pinpoint sensitive regions in private photos with an explainable deep learning-based approach. Our evaluations show that AutoPri can effectively determine user-specific private photos with high accuracy (94.32%) and pinpoint exact sensitive regions in them to enable effective privacy control in user-centered online social networks.
KW - deep learning
KW - privacy control
KW - social media
UR - http://www.scopus.com/inward/record.url?scp=85130616647&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85130616647&partnerID=8YFLogxK
U2 - 10.1145/3508398.3511517
DO - 10.1145/3508398.3511517
M3 - Conference contribution
AN - SCOPUS:85130616647
T3 - CODASPY 2022 - Proceedings of the 12th ACM Conference on Data and Application Security and Privacy
SP - 65
EP - 76
BT - CODASPY 2022 - Proceedings of the 12th ACM Conference on Data and Application Security and Privacy
PB - Association for Computing Machinery, Inc
T2 - 12th ACM Conference on Data and Application Security and Privacy, CODASPY 2022
Y2 - 24 April 2022 through 27 April 2022
ER -