Investigation, Detection and Prevention of Online Child Sexual Abuse Materials: A Comprehensive Survey

Ngox, Vuong M.; Thorpe, Christina; Dang, Cach N.; McKeever, Susan

doi:10.1109/rivf55975.2022.10013853

Cited by 4 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The production and distribution of CSAM have profound and detrimental impacts on both the victims and society as a whole. The victims of CSAM often endure long-lasting psychological, emotional, and physical harm as a result of the abuse they have experienced [1]. A high volume of CSAM is generated and shared on a daily basis, not only on surface web platforms like social network sites but also within dark web forums.…”

Section: Of 18mentioning

confidence: 99%

“…However, the remaining two forums, pharos and nymphetomania, have either a small number of or no available information regarding the number of CSAM creators, victim nationalities, platforms and topics. 1 The number of English CSAM posts. 2 The number of all English posts in the forum which include English CSAM posts and English non-CSAM posts.…”

Section: Our Dark Web Datamentioning

confidence: 99%

“…This can include photographs, videos, stories, chats, comments, drawings or any other form of media that portrays or discusses such abusive acts. 1 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Discovering child sexual abuse material creators' behaviors and preferences on the dark web

Ngo,

Gajula,

Thorpe

et al. 2024

Child Abuse & Neglect

View full text Add to dashboard Cite

Section: Of 18mentioning

confidence: 99%

Section: Our Dark Web Datamentioning

confidence: 99%

See 1 more Smart Citation

Discovering child sexual abuse material creators' behaviors and preferences on the dark web

Ngo,

Gajula,

Thorpe

et al. 2024

Child Abuse & Neglect

View full text Add to dashboard Cite

“…Recent Works The recent publication of a survey on detecting and preventing online child sexual abuse material [31] compares over 35 studies on the topic. The findings of this survey highlight the problem's complexity and the need to combine computer vision and natural language processing techniques to combat this heinous crime.…”

Section: Related Workmentioning

confidence: 99%

Metadata-Based Detection of Child Sexual Abuse Material

Pereira,

Dodhia,

Anderson

et al. 2024

IEEE Trans. Dependable and Secure Comput.

View full text Add to dashboard Cite

Child Sexual Abuse Media (CSAM) is any visual record of a sexually explicit activity involving minors. Machine learning-based solutions can help law enforcement identify CSAM and block distribution. Yet, collecting CSAM imagery to train machine learning models has ethical and legal constraints. CSAM detection systems based on file metadata offer several opportunities. Metadata is not a record of a crime and, therefore, clear of legal restrictions. This paper proposes a CSAM detection framework consisting of machine learning models trained on file paths extracted from a real-world data set of over 1 million file paths obtained in criminal investigations. Our framework includes guidelines for model evaluation that account for data changes caused by adversarial data modification and variations in data distribution caused by limited access to training data, as well as an assessment of false positive rates against file paths from common crawl data. We achieve accuracies as high as 0.97 while presenting stable behavior under adversarial attacks previously used in natural language tasks. When evaluating the model on publicly available file paths from common crawl data, we observed a false positive rate of 0.002, showing that the model operating in distinct data distributions maintains low false positive rates.

show abstract

A review of risk factors for online and mixed child sexual abuse material offending: what is being researched?

Reichel,

Daser,

Gnielka

et al. 2024

Journal of Sexual Aggression

View full text Add to dashboard Cite

Investigation, Detection and Prevention of Online Child Sexual Abuse Materials: A Comprehensive Survey

Cited by 4 publications

References 41 publications

Discovering child sexual abuse material creators' behaviors and preferences on the dark web

Discovering child sexual abuse material creators' behaviors and preferences on the dark web

Metadata-Based Detection of Child Sexual Abuse Material

A review of risk factors for online and mixed child sexual abuse material offending: what is being researched?

Contact Info

Product

Resources

About