DeepUAge: Improving Underage Age Estimation Accuracy to Aid CSEM Investigation

Anda, Felix; Le-Khac, Nhien-An; Scanlon, Mark

doi:10.1016/j.fsidi.2020.300921

Cited by 7 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work in this area requires the investigation of the relationships with these add-ons and the cyberlockers providing the illegal streams. In addition, much remains to be done with automated stream content analysis using computer vision to automatically detect illegal content [3,1]. As techniques are created to monetize such illicit services by cybercriminals, the need for the investigation of these machines will increase.…”

Section: Discussionmentioning

confidence: 99%

Retracing the Flow of the Stream: Investigating Kodi Streaming Services

Bromley¹,

Sheppard²,

Scanlon³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Kodi is of one of the world's largest open-source streaming platforms for viewing video content. Easily installed Kodi add-ons facilitate access to online pirated videos and streaming content by facilitating the user to search and view copyrighted videos with a basic level of technical knowledge. In some countries, there have been paid child sexual abuse organizations publishing/streaming child abuse material to an international paying clientele. Open source software used for viewing videos from the Internet, such as Kodi, is being exploited by criminals to conduct their activities. In this paper, we describe a new method to quickly locate Kodi artifacts and gather information for a successful prosecution. We also evaluate our approach on different platforms; Windows, Android and Linux. Our experiments show the file location, artifacts and a history of viewed content including their locations from the Internet. Our approach will serve as a resource to forensic investigators to examine Kodi or similar streaming platforms.

show abstract

Section: Discussionmentioning

confidence: 99%

Retracing the Flow of the Stream: Investigating Kodi Streaming Services

Bromley¹,

Sheppard²,

Scanlon³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…There is a growing body of research focusing solely on age estimation in the context of CSAM, and the collection of child images seems to be a common choice for many. Anda et al [3] propose a model specialized in underage individuals, building a novel dataset for age and gender estimation, VisAGe. They gathered over 19 thousand faces of individuals under 18 years old, from creative-commons licensed Flickr images.…”

Section: Csam Detectionmentioning

confidence: 99%

Seeing without Looking: Analysis Pipeline for Child Sexual Abuse Datasets

Laranjeira¹,

Macedo²,

Avila³

et al. 2022

Preprint

View full text Add to dashboard Cite

The online sharing and viewing of Child Sexual Abuse Material (CSAM) are growing fast, such that human experts can no longer handle the manual inspection. However, the automatic classification of CSAM is a challenging field of research, largely due to the inaccessibility of target data that is -and should forever be -private and in sole possession of law enforcement agencies. To aid researchers in drawing insights from unseen data and safely providing further understanding of CSAM images, we propose an analysis template that goes beyond the statistics of the dataset and respective labels. It focuses on the extraction of automatic signals, provided both by pre-trained machine learning models, e.g., object categories and pornography detection, as well as image metrics such as luminance and sharpness. Only aggregated statistics of sparse signals are provided to guarantee the anonymity of children and adolescents victimized. The pipeline allows filtering the data by applying thresholds to each specified signal and provides the distribution of such signals within the subset, correlations between signals, as well as a bias evaluation. We demonstrated our proposal on the Region-based annotated Child Pornography Dataset (RCPD), one of the few CSAM benchmarks in the literature, composed of over 2000 samples among regular and CSAM images, produced in partnership with Brazil's Federal Police. Although noisy and limited in several senses, we argue that automatic signals can highlight important aspects of the overall distribution of data, which is valuable for databases that can not be disclosed. Our goal is to safely publicize the characteristics of CSAM datasets, encouraging researchers to join the field and perhaps other institutions to provide similar reports on their benchmarks.

show abstract

“…Another relevant CV area is age estimation. In 2020, Anda et al [7], proposed the segregation of the age component from a CSEM investigative model. This approach tackles specifically the facial age estimation problem for underage subjects, which can be further consolidated with a nudity component to create a CSEM ensemble.…”

Section: State Of the Art Of Ai On Computer Visionmentioning

confidence: 99%

SoK

Hargreaves

Sheppard

et al. 2020

Proceedings of the 15th International Conference on Availability, Reliability and Security

Self Cite

View full text Add to dashboard Cite

Multi-year digital forensic backlogs have become commonplace in law enforcement agencies throughout the globe. Digital forensic investigators are overloaded with the volume of cases requiring their expertise compounded by the volume of data to be processed. Artificial intelligence is often seen as the solution to many big data problems. This paper summarises existing artificial intelligence based tools and approaches in digital forensics. Automated evidence processing leveraging artificial intelligence based techniques shows great promise in expediting the digital forensic analysis process while increasing case processing capacities. For each application of artificial intelligence highlighted, a number of current challenges and future potential impact is discussed.

show abstract

DeepUAge: Improving Underage Age Estimation Accuracy to Aid CSEM Investigation

Cited by 7 publications

References 13 publications

Retracing the Flow of the Stream: Investigating Kodi Streaming Services

Retracing the Flow of the Stream: Investigating Kodi Streaming Services

Seeing without Looking: Analysis Pipeline for Child Sexual Abuse Datasets

SoK

Contact Info

Product

Resources

About