Detecting child sexual abuse material: A comprehensive survey

@article{Lee2020DetectingCS,
  title={Detecting child sexual abuse material: A comprehensive survey},
  author={Hee-Eun Lee and Tatiana Ermakova and Vasilis Ververis and Benjamin Fabian},
  journal={Digit. Investig.},
  year={2020},
  volume={34},
  pages={301022}
}
Child Sexual Abuse and the Internet—A Systematic Review
Child sexual abuse is a growing social concern. Today, online communication chiefly facilitates access to vulnerable children and increases cases of child sexual abuse. The current article also aims
“Our Laws Have Not Caught up with the Technology”: Understanding Challenges and Facilitators in Investigating and Prosecuting Child Sexual Abuse Materials in the United States
With technological advances, the creation and distribution of child sexual abuse material (CSAM) has become one of the fastest growing illicit online industries in the United States. Perpetrators are
Pornographic content classification using deep-learning
TLDR
This paper addresses pornography detection by creating a model capable of locating and labelling sexual organs in images and extending this model to perform image classification to provide the user with one of 19 semantically meaningful descriptors of the content.
A Unified Taxonomy of Harmful Content
TLDR
The most common types of abuse described by industry, policy, community and health experts are synthesized into a unified typology of harmful content, with detailed criteria and exceptions for each type of abuse.
Do You See What I See? Capabilities and Limits of Automated Multimedia Content Analysis
TLDR
The capabilities and limitations of tools for analyzing online multimedia content are explained and the potential risks of using these tools at scale without accounting for their limitations are highlighted.
The Comparison Performance of Digital Forensic Tools Using Additional Root Access Options
TLDR
The result of this study shows that the cases studied with processes without root access and with root access have the aim of complementing each other in obtaining evidence, and the recommended tool according to the used scenario is Magnet Axiom.
Religion, Morality, Ethics, and Problematic Pornography Use
The present review focuses on relationships between sexuality and religion, moral values, and ethics. Religious and ethical beliefs and moral values may influence sexuality including perception of
Design and Implementation of It Job Recruitment Data Based on Web Crawler
TLDR
Python web crawler technology is used to obtain job information of recruitment website and store it in database, XPath module is used in to clean and crawl job data, and Struts2+hibernate is use to realize employment recommendation system.

References

SHOWING 1-10 OF 48 REFERENCES
Tutorial-1: New criminal and victim identification methods for sexual offenses against women and children
  • Adams Wai Kin Kong
  • Psychology
    2015 IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE)
  • 2015
With recent advances in Internet and multimedia technology, the involvement of digital images in sexual offenses against women and children has been increasing significantly. These sexual offenses
Pornography and child sexual abuse detection in image and video: A comparative evaluation
TLDR
This study observes that for pornography or CSA detection, the methods involving multiple features perform better than those using simple features like skin color or single image descriptor, and finds that deep learning based methods outperform all of the other methods and report current state-of-the-art.
Automatic detection of child pornography using color visual words
  • A. Ulges, A. Stahl
  • Computer Science
    2011 IEEE International Conference on Multimedia and Expo
  • 2011
TLDR
This paper introduces a system which employs visual recognition techniques to automatically identify suspect material based on color-enhanced visual word features and a statistical classification using SVMs, and illustrates that the system employs color cues as key features for discriminating CSA content.
Behavioural Evidence Analysis Applied to Digital Forensics: An Empirical Analysis of Child Pornography Cases Using P2P Networks
TLDR
Forensic analysis of 15 SEIC cases involving P2P file sharing networks, obtained from the Dubai Police confirmed the predicted benefits and indicate that BEA can assist digital forensic practitioners and prosecutors.
How to Look: Apprehension, Forensic Craft, and the Classification of Child Exploitation Images
The detection and removal of child pornography online is a vexing process, weighted with moral urgency. In recent years, this process has become increasingly digitally automated. In 2016, the
iCOP: Automatically Identifying New Child Abuse Media in P2P Networks
TLDR
A novel approach that combines sophisticated filename and media analysis techniques to automatically flag new previously unseen CSA media to investigators is presented, implemented into the iCOP toolkit and shows high degrees of accuracy.
Automatic Detection of CSA Media by Multi-modal Feature Fusion for Law Enforcement Support
TLDR
This paper addresses the automatic detection of CSA material in image and video data by multi-modal feature description by applying multiple low level features as well as SentiBank, a novel mid-level representation of visual content to achieve improved detection accuracy.
Assessing the Validity of Automated Webcrawlers as Data Collection Tools to Investigate Online Child Sexual Exploitation
TLDR
This work compares networks starting from CE websites to those from similar non-CE sexuality websites and dissimilar sports websites to provide evidence that webcrawlers have the potential to provide valid CE data, if the appropriate criterion is selected.
A Statistical Approach for Identifying Videos of Child Pornography at Crime Scenes
  • M. Polastro, P. Eleuterio
  • Computer Science
    2012 Seventh International Conference on Availability, Reliability and Security
  • 2012
TLDR
Experiments showed that the new approach is quick enough to be performed at crime scenes with detection rates around 85%, bringing new benefits for forensic examiners in the identification of child pornographic files.
...
1
2
3
4
5
...