Advertisement

Forensic Detection of Child Exploitation Material Using Deep Learning

  • Mofakharul IslamEmail author
  • Abdun Nur Mahmood
  • Paul Watters
  • Mamoun Alazab
Chapter
Part of the Advanced Sciences and Technologies for Security Applications book series (ASTSA)

Abstract

A precursor to successful automatic child exploitation material recognition is the ability to automatically identify pornography (largely solved) involving children (largely unsolved). Identifying children’s faces in images previously labelled as pornographic can provide a solution. Automatic child face detection plays an important role in online environments by facilitating Law Enforcing Agencies (LEA) to track online child abuse, bullying, sexual assault, but also can be used to detect cybercriminals who are targeting children to groom up them with a view of molestation later. Previous studies have investigated this problem in an attempt to identify only children faces from a pool of adult faces, which aims to extract information from the basic low- and high-level features i.e., colour, texture, skin tone, shape, facial structures etc. on child and adult faces. Typically, this is a machine learning-based architecture that accomplish a categorization task with the aim of identifying a child face, given a set of child and adult faces using classification technique based on extracted features from the training images. In this paper, we present a deep learning methodology, where machine learns the features straight away from the training images without having any information provided by humans to identify children faces. Compared to the results published in a couple of recent work, our proposed approach yields the highest precision and recall, and overall accuracy in recognition.

Keywords

Child exploitation Child pornography Digital forensics Intelligence analysis Deep learning Cybercrime 

References

  1. 1.
    Kwon YH, da Lobo Vitoria N (1993) Locating facial features for age classification. In: Proceedings of SPIE – the International Society for Optical Engineering, vol 2055. SPIE – The International Society for Optical Engineering, Bellingham, pp 62–72Google Scholar
  2. 2.
    Kwon YH, Lobo N (1999) Age classification from facial images. Comput Vis Image Underst 74(1):1–21CrossRefGoogle Scholar
  3. 3.
    Hayashi J et al (2001) Method for estimating and modeling age and gender using facial image processing. In: Seventh international conference on virtual systems and multimedia. IEEE Computer Society, Los Alamitos, pp 439–448CrossRefGoogle Scholar
  4. 4.
    Lanitis A et al (2004) Comparing different classifiers for automatic age estimation. IEEE Trans Syst Man Cybern B 34(1):621–628CrossRefGoogle Scholar
  5. 5.
    Cootes TF et al (2001) Active appearance models. IEEE Trans Pattern Anal Mach Intell 23:681–684CrossRefGoogle Scholar
  6. 6.
    Yan S et al (2007) Auto-structured regressor from uncertain labels. In: International conference on computer visionGoogle Scholar
  7. 7.
    Khoa L et al (2009) Age estimation using active appearance models and support vector machine regression, biometrics: theory, applications, and systems, 2009. BTAS ’09. IEEE 3rd international conference. Washington, USA, pp 1–5Google Scholar
  8. 8.
    Geng X et al (2007) Automatic age estimation based on facial aging patterns. IEEE Trans Pattern Anal Mach Intell 29(12):2234–2240CrossRefGoogle Scholar
  9. 9.
    Fu Y, Huang TS (2008) Human age estimation with regression on discriminative aging manifold. IEEE Trans Multimed 10(4):578–584CrossRefGoogle Scholar
  10. 10.
    Guo G et al (2008) Image-based human age estimation by manifold learning and locally adjusted robust regression. IEEE Trans Image Process 17(7):1178–1188MathSciNetCrossRefGoogle Scholar
  11. 11.
    Yan S et al (2009) Synchronized submanifold embedding for person independent pose estimation and beyond. IEEE Trans Image Process 18(1):202–210MathSciNetCrossRefGoogle Scholar
  12. 12.
    Krizhevsky A (2012) ImageNet classification with deep convolutional neural networks, In: Advances in neural information processing systems, pp 1097–1105Google Scholar
  13. 13.
    NCMEC, National Center for Missing & Exploited Children (NCMEC). http://www.missingkids.com
  14. 14.
    Face and Gesture Recognition Research Network. http://www.fgnet.rsunit.com/
  15. 15.
    Simon B (2017) Large age-gap face verification by feature injection in deep networks. Pattern Recogn Lett 90.  https://doi.org/10.1016/j.patrec.2017.03.006 CrossRefGoogle Scholar
  16. 16.
    Chang CC, Lin C-J (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2 (1):27. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm CrossRefGoogle Scholar
  17. 17.
    Islam M et al (2011) Child face detection using age specific luminance invariant geometric descriptor. In: 2011 IEEE international conference on signal and image processing applications (ICSIPA2011)Google Scholar
  18. 18.
    Watters PA (2018) Investigating malware epidemiology and child exploitation using algorithmic ethnography. In: Proceedings of the 51st Hawaii International Conference on Systems Science (HICSS), HawaiiGoogle Scholar
  19. 19.
    Watters PA (2018) Modelling the efficacy of auto-internet warnings to reduce demand for child exploitation material. In: Proceedings of the 22nd Asia-Pacific conference on knowledge discovery and data mining workshopsGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Mofakharul Islam
    • 1
    Email author
  • Abdun Nur Mahmood
    • 1
  • Paul Watters
    • 1
  • Mamoun Alazab
    • 2
  1. 1.Department of Computer Science and Information TechnologyLa Trobe UniversityMelbourneAustralia
  2. 2.Charles Darwin UniversityCasuarinaAustralia

Personalised recommendations