TY - GEN
T1 - Toward automated multiparty privacy conflict detection
AU - Zhong, Haoti
AU - Squicciarini, Anna
AU - Miller, David
N1 - Funding Information:
Our results are thus far based on the simpler case of one uploader and one stakeholder. Clearly, this may not always be the case, as more users are present in a single piece of content. While the model is designed to support any number of stakeholders, we are yet to validate this case empirically. While our use of four privacy label values is a de-facto standard, a more fine grained representation of users’ privacy preferences (e.g. by audience groups) could help improve generalizability of our approach. Due to space limitations we have so far reported only the main findings from our model. It would be important to expand the empirical evaluation and give an extensive treatment of cases where users have no historical data. Acknowledgments Work from Dr Squicciarini and Haoti Zhong was partially funded by National Science Foundation under grant 1421776 and 1453080.
Publisher Copyright:
© 2018 Association for Computing Machinery.
PY - 2018/10/17
Y1 - 2018/10/17
N2 - In an effort to support users' decision making process in regards to shared and co-managed online images, in this paper we present a novel model to early detect images which may be subject to possible conflicting access control decisions. We present a group-based stochastic model able to identify potential privacy conflicts among multiple stakeholders of an image. We discuss experiments on a dataset of over 3000 online images. Our approach outperforms all baselines, even the strong ones based on a Convolutional Neural Network architecture.
AB - In an effort to support users' decision making process in regards to shared and co-managed online images, in this paper we present a novel model to early detect images which may be subject to possible conflicting access control decisions. We present a group-based stochastic model able to identify potential privacy conflicts among multiple stakeholders of an image. We discuss experiments on a dataset of over 3000 online images. Our approach outperforms all baselines, even the strong ones based on a Convolutional Neural Network architecture.
UR - http://www.scopus.com/inward/record.url?scp=85058040473&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85058040473&partnerID=8YFLogxK
U2 - 10.1145/3269206.3269329
DO - 10.1145/3269206.3269329
M3 - Conference contribution
AN - SCOPUS:85058040473
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 1811
EP - 1814
BT - CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management
A2 - Paton, Norman
A2 - Candan, Selcuk
A2 - Wang, Haixun
A2 - Allan, James
A2 - Agrawal, Rakesh
A2 - Labrinidis, Alexandros
A2 - Cuzzocrea, Alfredo
A2 - Zaki, Mohammed
A2 - Srivastava, Divesh
A2 - Broder, Andrei
A2 - Schuster, Assaf
PB - Association for Computing Machinery
T2 - 27th ACM International Conference on Information and Knowledge Management, CIKM 2018
Y2 - 22 October 2018 through 26 October 2018
ER -