tutorial

Automatic Detection of CSA Media by Multi-modal Feature Fusion for Law Enforcement Support

Authors:

Christian Schulze,

Dominik Henter,

Andreas DengelAuthors Info & Claims

ICMR '14: Proceedings of International Conference on Multimedia Retrieval

Pages 353 - 360

https://doi.org/10.1145/2578726.2578772

Published: 01 April 2014 Publication History

Abstract

The growing amounts of multimedia data being made available and shared via the Internet pose an increasing problem for law enforcement to investigate the distribution and possession of child sexual abuse (CSA) media. In this paper we address the automatic detection of CSA material in image and video data by multi-modal feature description. Instead of analyzing hash sums or file names, we propose the content-based analysis on visual and, in case of videos, also audio features. To this end, we apply multiple low level features as well as SentiBank, a novel mid-level representation of visual content. In collaboration with police partners and European cyber crime units, we conducted experiments on several datasets, including real world CSA media. Our quantitative evaluation reveals the challenging nature of child pornography detection, especially in the joint presence of non-illegal pornographic data, rendering skin detection, a popular feature for detecting pornography, less discriminative. Further, the utilization of SentiBank features shows high potential for detection and explainability of such content. Overall, multi-modal feature fusion can achieve an improved detection accuracy, reducing equal error rate from 17% to 10% for images and from 16% to 8% for videos as compared to best single feature performance for the challenging task of classifying CSA content from adult media.

References

[1]

PhotoDNA. Microsoft Information Site; available from http://www.microsoft.com/en-us/news/presskits/photodna/ (retrieved: Nov'13).

[2]

D. Borth, R. Ji, T. Chen, T. Breuel, and S.-F. Chang. Large-scale Visual Sentiment Ontology and Detectors Using Adjective Noun Pairs. In ACM Multimedia, 2013.

Digital Library

[3]

Yi Chan, Richard Harvey, and Dan Smith. Building systems to block pornography. In Proceedings of the 1999 International Conference on Challenge of Image Retrieval, IM'99, pages 8--8, Swinton, UK, UK, 1999. British Computer Society.

Digital Library

[4]

T. Deselaers, L. Pimenidis, and H. Ney. Bag-of-Visual-Words Models for Adult Image Classification and Filtering. In ICPR, pages 1--4, 2008.

[5]

P. da Silva Eleuterio and M. de Castro Polastro. An adaptive sampling strategy for automatic detection of child pornographic videos. In Int. Conf. on Forensic Computer Science, pages 12--19, 2012.

[6]

M. M. Fleck, D. A. Forsyth, and C. Bregler. Finding Naked People. In ECCV, pages 593--602, 1996.

Digital Library

[7]

Jing Huang, S.R. Kumar, M. Mitra, Wei-Jing Zhu, and R. Zabih. Image Indexing Using Color Correlograms. In CVPR, pages 762--768, 1997.

Digital Library

[8]

C. Jansohn, A. Ulges, and T. Breuel. Detecting Pornographic Video Content by Combining Image Featureswith Motion Information. In ACM Multimedia, 2009.

Digital Library

[9]

M. Jones and J. Rehg. Statistical Color Models with Application to Skin Detection. Int. J. Comput. Vision, 46(1):81--96, January 2002.

Digital Library

[10]

M.J. Jones and J.M. Rehg. Statistical color models with application to skin detection. In CVPR, 1999.

[11]

C.-Y.l Kim, O.-J. Kwon, W.-G. Kim, and S.-R. Choi. Automatic System for Filtering Obscene Video. In Advanced Communication Technology, 2008. ICACT 2008. 10th International Conference on, volume 2, pages 1435--1438, 2008.

[12]

M. Latapy, C. Magnien, and G. Valadon. First Report on Database Specification and Access including Content Rating and Fake Detection System. Technical report, Measurement and Analysis of P2P Activity Against Paedophile Content (MAPAP) Project, 2008.

[13]

S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, volume 2, pages 2169--2178, 2006.

Digital Library

[14]

Hogyun Lee, Seungmin Lee, and Taekyong Nam. Implementation of high performance objectionable video classification system. ICACT, pages 959--962, 2006.

[15]

H.-T. Lin, C.-J. Lin, and R. Weng. A Note on Platt's Probabilistic Outputs for Support Vector Machines. Mach. Learn., 68(3):267--276, 2007.

Digital Library

[16]

Y. Liu, X. Wang, Y. Zhang, and S. Tang. Fusing Audio-Words with Visual Features for Pornographic Video Detection. In Proc. TRUSTCOM'11, pages 1488--1493, 2011.

Digital Library

[17]

B. Logan. Mel Frequency Cepstral Coefficients for Music Modeling. In Int. Symposium on Music Inf. Retrieval, 2000.

[18]

LTU Engine. available from http://www.ltutech.com/en/products/ltu-engine-2 (retrieved: June 2010).

[19]

Netclean Analyze. available from http://www.netclean.com/ (retrieved: June 2010).

[20]

T. Ojala, M. Rautiainen, E. Matinmikko, and M. Aittola. Semantic Image Retrieval with HSV Correlograms. In Proceedings of the 12th Scandinavian Conference on Image Analysis, pages 621--627, 2001.

[21]

L. Rabiner and B.-H. Juang. Fundamentals of Speech Recognition. Prentice-Hall, Inc., 1993.

Digital Library

[22]

M. Rautiainen and T. Ojala. Color Correlograms in Image and Video Retrieval. In Proceedings of the 10th Finnish Artificial Intelligence Conference (STeP2002), pages 203--212, 2002.

[23]

H. Rowley, Y. Jing, and S. Baluja. Large Scale Image-Based Adult-Content Filtering. In Int. Conf. Comp. Vis. Theory and Applications, pages 290--296, February 2006.

[24]

A. Shupo, M. Martin, L. Rueda, A. Bulkan, Y. Chen, and P. Hung. Toward Efficient Detection of Child Pornography in the Network Infrastructure. Int. J. on Computer Science and Information Systems, 1(2):15--31, 2006.

[25]

P. Skulsujirapa, S. Aramvith, and S. Siddhichai. Development of Digital Image Retrieval Technique using Autocorrelogram and Wavelet Based Texture. In Circuits and Systems, 2004. MWSCAS '04. The 2004 47th Midwest Symposium on, volume 1, pages I--273--6 vol.1, 2004.

[26]

Xiaofeng T., L. Duan, C. Xu, Q. Tian, Hanqing L., J. Wang, and J.S. Jin. Periodicity Detection of Local Motion. Multimedia and Expo, 2005. ICME 2005. IEEE International Conference on, pages 650--653, July 2005.

[27]

A. Ulges, C. Schulze, D. Borth, and A. Stahl. Pornography detection in video benefits (a lot) from a multi-modal approach. In Workshop on Audio and Multimedia Methods for Large-Scale Video Analysis (AMVA-2012). ACM, 2012.

Digital Library

[28]

A. Ulges and A. Stahl. Automatic Detection of Child Pornography using Color Visual Words. In Proc. Int. Conf. Multimedia and Expo, July 2011.

Digital Library

[29]

Zheng-Jun Zha, Yuan Liu, Tao Mei, and Xian-Sheng Hua. Video concept detection using support vector machines - trecvid 2007 evaluations. Technical report, 2008.

[30]

H. Zuo, O. Wu an W. Hu, and B. Xu. Recognition of Blue Movies by Fusion of Audio and Video. In Proc. ICME, pages 37--40, 2008.

Cited By

Povedano Álvarez DSandoval Orozco AGarcía-Miguel JGarcía Villalba L(2023)Learning Strategies for Sensitive Content DetectionElectronics10.3390/electronics1211249612:11(2496)Online publication date: 1-Jun-2023
https://doi.org/10.3390/electronics12112496
Zhang ZYang JMagalhães Jdel Bimbo ASatoh SSebe NAlameda-Pineda XJin QOria VToni L(2022)Temporal Sentiment Localization: Listen and Look in Untrimmed VideosProceedings of the 30th ACM International Conference on Multimedia10.1145/3503161.3548007(199-208)Online publication date: 10-Oct-2022
https://dl.acm.org/doi/10.1145/3503161.3548007
Spalazzi LPaolanti MFrontoni E(2022)An offline parallel architecture for forensic multimedia classificationMultimedia Tools and Applications10.1007/s11042-021-10819-x81:16(22715-22730)Online publication date: 1-Jul-2022
https://dl.acm.org/doi/10.1007/s11042-021-10819-x
Show More Cited By

Index Terms

Automatic Detection of CSA Media by Multi-modal Feature Fusion for Law Enforcement Support
1. Information systems
  1. Information retrieval

Recommendations

Digital crime investigation trends in state and local law enforcement
The art of trolling law enforcement: a review and model for implementing ‘flame trolling' legislation enacted in Great Britain 1981–2012

The advancement of information and communications technology often results in early adoption, followed by concern over a digital divide, followed by mass adoption and then, inevitably, abuse and misuse of that platform. The most recent of these ...
Perceptions of University Law Enforcement Officials’ Regarding Unsubmitted, Untested Sexual Assault Kits (SAKS)

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

ICMR '14: Proceedings of International Conference on Multimedia Retrieval

April 2014

564 pages

ISBN:9781450327824

DOI:10.1145/2578726

Conference Chairs:
Mohan Kankanhalli
National University of Singapore
,
Stefan Rueger
The Open University, UK
,
R. Manmatha
A9.com, USA
,
General Chairs:
Joemon Jose
University of Glasgow, UK
,
Keith van Rijsbergen
University of Glasgow, UK

Copyright © 2014 Owner/Author.

Permission to make digital or hard copies of part or all 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 third-party components of this work must be honored. For all other uses, contact the Owner/Author.

In-Cooperation

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 April 2014

Check for updates

Author Tags

Qualifiers

Tutorial
Research
Refereed limited

Conference

ICMR '14

ICMR '14: International Conference on Multimedia Retrieval

April 1 - 4, 2014

Glasgow, United Kingdom

Acceptance Rates

ICMR '14 Paper Acceptance Rate 21 of 111 submissions, 19%;

Overall Acceptance Rate 254 of 830 submissions, 31%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

11
Total Citations
View Citations
318
Total Downloads

Downloads (Last 12 months)15
Downloads (Last 6 weeks)4

Reflects downloads up to 28 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Povedano Álvarez DSandoval Orozco AGarcía-Miguel JGarcía Villalba L(2023)Learning Strategies for Sensitive Content DetectionElectronics10.3390/electronics1211249612:11(2496)Online publication date: 1-Jun-2023
https://doi.org/10.3390/electronics12112496
Zhang ZYang JMagalhães Jdel Bimbo ASatoh SSebe NAlameda-Pineda XJin QOria VToni L(2022)Temporal Sentiment Localization: Listen and Look in Untrimmed VideosProceedings of the 30th ACM International Conference on Multimedia10.1145/3503161.3548007(199-208)Online publication date: 10-Oct-2022
https://dl.acm.org/doi/10.1145/3503161.3548007
Spalazzi LPaolanti MFrontoni E(2022)An offline parallel architecture for forensic multimedia classificationMultimedia Tools and Applications10.1007/s11042-021-10819-x81:16(22715-22730)Online publication date: 1-Jul-2022
https://dl.acm.org/doi/10.1007/s11042-021-10819-x
Rondeau JDeslauriers DHoward III TAlvarez M(2022)A deep learning framework for finding illicit images/videos of childrenMachine Vision and Applications10.1007/s00138-022-01318-633:5Online publication date: 1-Sep-2022
https://dl.acm.org/doi/10.1007/s00138-022-01318-6
Yaqub WMohanty MMemon N(2018)Encrypted Domain Skin Tone Detection For Pornographic Image Filtering2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)10.1109/AVSS.2018.8639350(1-5)Online publication date: Nov-2018
https://doi.org/10.1109/AVSS.2018.8639350
Vitorino PAvila SPerez MRocha A(2018)Leveraging deep neural networks to fight child pornography in the age of social mediaJournal of Visual Communication and Image Representation10.1016/j.jvcir.2017.12.00550:C(303-313)Online publication date: 1-Jan-2018
https://dl.acm.org/doi/10.1016/j.jvcir.2017.12.005
Luo JBorth DYou QLiu QLienhart RWang HChen SBoll SChen PFriedland GLi JYan S(2017)Social Multimedia Sentiment AnalysisProceedings of the 25th ACM international conference on Multimedia10.1145/3123266.3130143(1953-1954)Online publication date: 23-Oct-2017
https://dl.acm.org/doi/10.1145/3123266.3130143
Chatzis VPanagiotopoulos FMardiris V(2016)Face to Iris Area Ratio as a feature for children detection in digital forensics applications2016 Digital Media Industry & Academic Forum (DMIAF)10.1109/DMIAF.2016.7574915(121-124)Online publication date: Jul-2016
https://doi.org/10.1109/DMIAF.2016.7574915
Al-Naser MChanijani SBukhari SBorth DDengel ASoleymani MYang YJiang YChang S(2015)What Makes a Beautiful Landscape BeautifulProceedings of the 1st International Workshop on Affect & Sentiment in Multimedia10.1145/2813524.2813532(51-56)Online publication date: 30-Oct-2015
https://dl.acm.org/doi/10.1145/2813524.2813532
Peersman CSchulze CRashid ABrennan MFischer C(2014)iCOPProceedings of the 2014 IEEE Security and Privacy Workshops10.1109/SPW.2014.27(124-131)Online publication date: 17-May-2014
https://dl.acm.org/doi/10.1109/SPW.2014.27
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten