Nothing Special   »   [go: up one dir, main page]

skip to main content
10.1145/3308558.3313691acmotherconferencesArticle/Chapter ViewAbstractPublication PagesthewebconfConference Proceedingsconference-collections
research-article

Dynamic Deep Multi-modal Fusion for Image Privacy Prediction

Published: 13 May 2019 Publication History

Abstract

With millions of images that are shared online on social networking sites, effective methods for image privacy prediction are highly needed. In this paper, we propose an approach for fusing object, scene context, and image tags modalities derived from convolutional neural networks for accurately predicting the privacy of images shared online. Specifically, our approach identifies the set of most competent modalities on the fly, according to each new target image whose privacy has to be predicted. The approach considers three stages to predict the privacy of a target image, wherein we first identify the neighborhood images that are visually similar and/or have similar sensitive content as the target image. Then, we estimate the competence of the modalities based on the neighborhood images. Finally, we fuse the decisions of the most competent modalities and predict the privacy label for the target image. Experimental results show that our approach predicts the sensitive (or private) content more accurately than the models trained on individual modalities (object, scene, and tags) and prior privacy prediction works. Also, our approach outperforms strong baselines, that train meta-classifiers to obtain an optimal combination of modalities.

References

[1]
Shane Ahern, Dean Eckles, Nathaniel S. Good, Simon King, Mor Naaman, and Rahul Nair. 2007. Over-exposed?: privacy patterns and considerations in online and mobile photo sharing. In CHI '07.
[2]
Andrew Besmer and Heather Lipford. 2009. Tagged photos: concerns, perceptions, and protections. In CHI '09.
[3]
Avrim Blum and Tom Mitchell. 1998. Combining Labeled and Unlabeled Data with Co-training. In Proceedings of the Eleventh Annual Conference on Computational Learning Theory(COLT' 98). ACM, New York, NY, USA, 92-100.
[4]
Leo Breiman. 1996. Bagging predictors. Machine Learning 24, 2 (1996), 123-140.
[5]
Leo Breiman. 1996. Stacked Regressions. Machine Learning 24, 1 (1996), 49-64.
[6]
Daniel Buschek, Moritz Bader, Emanuel von Zezschwitz, and Alexander De Luca. 2015. Automatic Privacy Classification of Personal Photos. In INTERACT 2015.
[7]
Paulo Rodrigo Cavalin, Robert Sabourin, and Ching Y. Suen. 2011. Dynamic selection approaches for multiple classifier systems. Neural Computing and Applications 22 (2011), 673-688.
[8]
Ronan Collobert, Jason Weston, Le´on Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. Natural Language Processing (Almost) from Scratch. J. Mach. Learn. Res. 12 (Nov. 2011), 2493-2537.
[9]
Rafael Cruz, Robert Sabourin, and George Cavalcanti. 2018. Dynamic classifier selection: Recent advances and perspectives. Information Fusion 41 (05 2018).
[10]
Rafael Cruz, Robert Sabourin, George Cavalcanti, and Tsang Ing Ren. 2015. META-DES: A dynamic ensemble selection framework using meta-learning. Pattern Recognition 48 (05 2015).
[11]
Olivier Debeir, Isabelle Van Den Steen, Patrice Latinne, Philippe Van Ham, and Eleonore Wolff. 2002. Textural and Contextual Land-Cover Classification Using Single and Multiple Classifier Systems. Photogrammetric Engineering and Remote Sensing 68 (2002), 597-605.
[12]
C. Feichtenhofer, A. Pinz, and A. Zisserman. 2016. Convolutional Two-Stream Network Fusion for Video Action Recognition. In IEEE CVPR.
[13]
Findlaw. 2017. Is It Safe to Post Photos of Your Kids Online?http://consumer.findlaw.com/online-scams/ is-it-safe-to-post-photos-of-your-kids-online.html.
[14]
Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc' Aurelio Ranzato, and Tomas Mikolov. 2013. DeViSE: A Deep Visual-Semantic Embedding Model. In NIPS. 2121-2129.
[15]
Kambiz Ghazinour, Stan Matwin, and Marina Sokolova. 2013. Monitoring and Recommending Privacy Settings in Social Networks. In Proceedings of the Joint EDBT/ICDT 2013 Workshops. 5.
[16]
Yunchao Gong, Liwei Wang, Micah Hodosh, Julia Hockenmaier, and Svetlana Lazebnik. 2014. Improving Image-Sentence Embeddings Using Large Weakly Annotated Photo Collections. In Computer Vision - ECCV 2014. 529-545.
[17]
Ralph Gross and Alessandro Acquisti. 2005. Information Revelation and Privacy in Online Social Networks. In Proceedings of the 2005 ACM Workshop on Privacy in the Electronic Society. 71-80.
[18]
Matthieu Guillaumin, Jakob Verbeek, and Cordelia Schmid. 2010. Multimodal semi-supervised learning for image classification., 902-909 pages.
[19]
Panagiotis Ilia, Iasonas Polakis, Elias Athanasopoulos, Federico Maggi, and Sotiris Ioannidis. 2015. Face/Off: Preventing Privacy Leakage From Photos in Social Networks. In Proceedings of the 22Nd ACM Conf. on Computer and Comm. Security.
[20]
Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. 2014. Caffe: Convolutional Architecture for Fast Feature Embedding. In Proceedings of the ACM International Conference on Multimedia. 675-678.
[21]
Simon Jones and Eamonn O'Neill. 2011. Contextual dynamics of group-based sharing decisions(CHI '11). 10.
[22]
A. Kannan, P. P. Talukdar, N. Rasiwasia, and Q. Ke. 2011. Improving Product Classification Using Images. In 2011 IEEE 11th Int. Conf. on Data Mining.
[23]
Ryan Kiros, Ruslan Salakhutdinov, and Rich Zemel. 2014. Multimodal Neural Language Models. In Proceedings of the 31st International Conf. on ML, Vol. 32.
[24]
Balachander Krishnamurthy and Craig E. Wills. 2008. Characterizing Privacy in Online Social Networks. In Proceedings of the First Workshop on Online Social Networks(WOSN '08). ACM, New York, NY, USA, 37-42.
[25]
Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In NIPS. 1097-1105.
[26]
Mark Laan, Eric C Polley, and Alan Hubbard. 2007. Super Learner. Statistical applications in genetics and molecular biology 6 (02 2007), Article 25.
[27]
Quoc Le and Tomas Mikolov. 2014. Distributed Representations of Sentences and Documents. In ICML(JMLR Workshop and Conf. Proceedings), Vol. 32. 1188-1196.
[28]
Yann LeCun. 2017. Facebook Envisions AI That Keeps You From Uploading Embarrassing Pics. https://www.wired.com/2014/12/fb/all/1.
[29]
Yifang Li, Wyatt Troutman, Bart P. Knijnenburg, and Kelly Caine. 2018. Human Perceptions of Sensitive Content in Photos. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops.
[30]
Heather Richter Lipford, Andrew Besmer, and Jason Watson. 2008. Understanding Privacy Settings in Facebook with an Audience View. In Proceedings of the 1st Conference on Usability, Psychology, and Security(UPSEC'08). 2:1-2:8.
[31]
D. Lu and Q. Weng. 2007. A survey of image classification methods and techniques for improving classification performance. Int. Journal of Remote Sensing(2007).
[32]
Corey Lynch, Kamelia Aryafar, and Josh Attenberg. 2016. Images Don'T Lie: Transferring Deep Visual Semantic Features to Large-Scale Multimodal Learning to Rank. In Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining(KDD '16). 541-548.
[33]
Mary Madden. 2012. Privacy management on social media sites. http://www.pewinternet.org/2012/02/24/privacy-management-on-social-media-sites.
[34]
Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, and Andrew Y. Ng. 2011. Multimodal Deep Learning. In Proceedings of the 28th International Conference on International Conference on Machine Learning(ICML'11).
[35]
Tribhuvanesh Orekondy, Bernt Schiele, and Mario Fritz. 2017. Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images. In IEEE International Conference on Computer Vision, ICCV 2017. 3706-3715.
[36]
J. Parra-Arnau, A. Perego, E. Ferrari, J. Forne´, and D. Rebollo-Monedero. 2014. Privacy-Preserving Enhanced Collaborative Tagging. IEEE Transactions on Knowledge and Data Engineering 26, 1 (Jan 2014), 180-193.
[37]
Javier Parra-Arnau, David Rebollo-Monedero, Jordi Forne´, Jose L. Mu&ntiled;oz, and Oscar Esparza. 2012. Optimal tag suppression for privacy protection in the semantic Web. Data Knowl. Eng. 81-82(2012), 46-66.
[38]
Soujanya Poria, Erik Cambria, Newton Howard, Guang-Bin Huang, and Amir Hussain. 2016. Fusing Audio, Visual and Textual Clues for Sentiment Analysis from Multimodal Content. Neurocomput. 174, PA (Jan. 2016), 50-59.
[39]
Nishkam Ravi, Nikhil Dandekar, Preetham Mysore, and Michael L. Littman. 2005. Activity Recognition from Accelerometer Data. In Proceedings of the 17th Conference on Innovative Applications of Artificial Intelligence. 1541-1546.
[40]
Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, and Li Fei-Fei. 2015. ImageNet Large Scale Visual Recognition Challenge. IJCV (April 2015), 1-42.
[41]
Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs/1409.1556(2014).
[42]
Andrew Simpson. 2008. On the Need for User-defined Fine-grained Access Control Policies for Social Networking Applications. In Proceedings of the Workshop on Security in Opportunistic and SOCial Networks(SOSOC '08). Article 1, 8 pages.
[43]
Marina Skurichina and Robert P.W. Duin. 1998. Bagging for linear classifiers. Pattern Recognition 31, 7 (1998), 909 - 930.
[44]
Eleftherios Spyromitros-Xioufis, Symeon Papadopoulos, Adrian Popescu, and Yiannis Kompatsiaris. 2016. Personalized Privacy-aware Image Classification. In Proceedings of the ACM on Int. Conf. on Multimedia Retrieval(ICMR '16). 71-78.
[45]
Anna Squicciarini, Cornelia Caragea, and Rahul Balakavi. 2014. Analyzing Images' Privacy for the Modern Web(HT '14). ACM, New York, NY, USA, 136-147.
[46]
Anna Squicciarini, Cornelia Caragea, and Rahul Balakavi. 2017. Toward Automated Online Photo Privacy. ACM TWeb 11, 1, Article 2 (2017), 2:1-2:29 pages.
[47]
Anna Squicciarini, Smitha Sundareswaran, Dan Lin, and Josh Wede. 2011. A3P: Adaptive Policy Prediction for Shared Images over Popular Content Sharing Sites. In Proceedings of the 22Nd ACM Conf. on Hypertext and Hypermedia. 261-270.
[48]
H. Sundaram, L. Xie, M. De Choudhury, Y.R. Lin, and A. Natsev. 2012. Multimedia Semantics: Interactions Between Content and Community. Proc. IEEE (2012).
[49]
Ashwini Tonge and Cornelia Caragea. 2016. Image Privacy Prediction Using Deep Features. In AAAI '16.
[50]
Ashwini Tonge and Cornelia Caragea. 2018. On the Use of “Deep” Features for Online Image Sharing. In Proceedings of The Web Conference Companion.
[51]
Ashwini Tonge, Cornelia Caragea, and Anna Squicciarini. 2018. Uncovering Scene Context for Predicting Privacy of Online Shared Images. In AAAI '18.
[52]
Lam Tran, Deguang Kong, Hongxia Jin, and Ji Liu. 2016. Privacy-CNH: A Framework to Detect Photo Privacy with Convolutional Neural Network Using Hierarchical Features. In AAAI '16. 7.
[53]
L. Wang, Zhe Wang, Wenbin Du, and Yu Qiao. 2015. Object-Scene Convolutional Neural Networks for Event Recognition in Images. CoRR abs/1505.00296(2015).
[54]
Susan Waters and James Ackerman. 2011. Exploring Privacy Management on Facebook: Motivations and Perceived Consequences of Voluntary Disclosure. Journal of Computer-Mediated Communication 17, 1 (2011), 101-115.
[55]
Jun Yu, Baopeng Zhang, Zhengzhong Kuang, Dan Lin, and Jianping Fan. 2017. iPrivacy: Image Privacy Protection by Identifying Sensitive Objects via Deep Multi-Task Learning. IEEE Trans. Information Forensics and Security 12, 5 (2017).
[56]
Tom Zahavy, Abhinandan Krishnan, Alessandro Magnani, and Shie Mannor. 2018. Is a Picture Worth a Thousand Words? A Deep Multi-Modal Architecture for Product Classification in E-Commerce. In AAAI. AAAI Press.
[57]
Sergej Zerr, Stefan Siersdorfer, Jonathon Hare, and Elena Demidova. 2012. Privacy-aware image classification and search. In ACM SIGIR. ACM, NY, USA.
[58]
Elena Zheleva and Lise Getoor. 2009. To Join or Not to Join: The Illusion of Privacy in Social Networks with Mixed Public and Private User Profiles. In WWW '09.
[59]
Haoti Zhong, Anna Squicciarini, David Miller, and Cornelia Caragea. 2017. A Group-Based Personalized Model for Image Privacy Classification and Labeling. In IJCAI' 17. 3952-3958.
[60]
B. Zhou, A. Khosla, A. Lapedriza, Antonio Torralba, and Aude Oliva. 2016. Places: An Image Database for Deep Scene Understanding. arXiv:1610.02055 (2016).

Cited By

View all
  • (2024)Intelligent System for Detection of Copyright-Protected Data for Enhanced Data SecurityBritish Journal of Computer, Networking and Information Technology10.52589/BJCNIT-OQQNPPCJ7:4(58-80)Online publication date: 17-Oct-2024
  • (2024)Visual privacy behaviour recognition for social robots based on an improved generative adversarial networkIET Computer Vision10.1049/cvi2.1223118:1(110-123)Online publication date: 8-Feb-2024
  • (2023)Deep Gated Multi-modal Fusion for Image Privacy PredictionACM Transactions on the Web10.1145/360844617:4(1-24)Online publication date: 10-Oct-2023
  • Show More Cited By

Recommendations

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences
WWW '19: The World Wide Web Conference
May 2019
3620 pages
ISBN:9781450366748
DOI:10.1145/3308558
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

  • IW3C2: International World Wide Web Conference Committee

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 13 May 2019

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Image privacy prediction
  2. decision-level fusion
  3. fusion of modalities

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

WWW '19
WWW '19: The Web Conference
May 13 - 17, 2019
CA, San Francisco, USA

Acceptance Rates

Overall Acceptance Rate 1,899 of 8,196 submissions, 23%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)49
  • Downloads (Last 6 weeks)4
Reflects downloads up to 25 Nov 2024

Other Metrics

Citations

Cited By

View all
  • (2024)Intelligent System for Detection of Copyright-Protected Data for Enhanced Data SecurityBritish Journal of Computer, Networking and Information Technology10.52589/BJCNIT-OQQNPPCJ7:4(58-80)Online publication date: 17-Oct-2024
  • (2024)Visual privacy behaviour recognition for social robots based on an improved generative adversarial networkIET Computer Vision10.1049/cvi2.1223118:1(110-123)Online publication date: 8-Feb-2024
  • (2023)Deep Gated Multi-modal Fusion for Image Privacy PredictionACM Transactions on the Web10.1145/360844617:4(1-24)Online publication date: 10-Oct-2023
  • (2023)Modality Coupling for Privacy Image ClassificationIEEE Transactions on Information Forensics and Security10.1109/TIFS.2023.330141418(4843-4853)Online publication date: 2023
  • (2023)DynamicMBFN: Dynamic Multimodal Bottleneck Fusion Network for Multimodal Emotion Recognition2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS)10.1109/ISCTIS58954.2023.10213035(639-644)Online publication date: 7-Jul-2023
  • (2023)Dual trustworthy mechanism for illness classification with multi-modality data2023 IEEE International Conference on Data Mining Workshops (ICDMW)10.1109/ICDMW60847.2023.00051(356-362)Online publication date: 4-Dec-2023
  • (2023)BRPPNetExpert Systems with Applications: An International Journal10.1016/j.eswa.2023.120960233:COnline publication date: 15-Dec-2023
  • (2023)Graphic image classification method based on an attention mechanism and fusion of multilevel and multiscale deep featuresComputer Communications10.1016/j.comcom.2023.07.001209(230-238)Online publication date: Sep-2023
  • (2023)Personalized Privacy Risk Assessment Based on Deep Neural Network for Image Sharing on Social NetworksAlgorithms and Architectures for Parallel Processing10.1007/978-981-97-0801-7_15(255-274)Online publication date: 20-Oct-2023
  • (2022)Privacy Intelligence: A Survey on Image Privacy in Online Social NetworksACM Computing Surveys10.1145/354729955:8(1-35)Online publication date: 23-Dec-2022
  • Show More Cited By

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media