Toward Detection of Child Exploitation Material: A Forensic Approach

Islam, Mofakharul; Watters, Paul A.; Mahmood, Abdun Nur; Alazab, Mamoun

doi:10.1007/978-3-030-13057-2_11

Cited by 3 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, a forensically sound process 2 , is one that integrates automated investigative analysis-evaluated through scientific (accuracy and precision) metricswith human assessments of the outcome. For example, a DF investigation into Child Sexual Exploitation Material (CSEM) [16,17] may seek to automatically detect and classify images of people found on a seized device as adult or underage (based on automatic estimated age). Because of possible misrepresentation in the dataset, misclassification (i.e., false positive), misinterpretation of features, and missing of critical features during the classification process that could have served as evidence (false negative; e.g., an underage wearing adult facial makeup) may occur [18].…”

Section: Methods For Evaluating Dfai Techniquesmentioning

confidence: 99%

Digital Forensics AI: Evaluating, Standardizing and Optimizing Digital Evidence Mining Techniques

Solanke

Biasiotti²

2022

Künstl Intell

View full text Add to dashboard Cite

The impact of AI on numerous sectors of our society and its successes over the years indicate that it can assist in resolving a variety of complex digital forensics investigative problems. Forensics analysis can make use of machine learning models’ pattern detection and recognition capabilities to uncover hidden evidence in digital artifacts that would have been missed if conducted manually. Numerous works have proposed ways for applying AI to digital forensics; nevertheless, scepticism regarding the opacity of AI has impeded the domain’s adequate formalization and standardization. We present three critical instruments necessary for the development of sound machine-driven digital forensics methodologies in this paper. We cover various methods for evaluating, standardizing, and optimizing techniques applicable to artificial intelligence models used in digital forensics. Additionally, we describe several applications of these instruments in digital forensics, emphasizing their strengths and weaknesses that may be critical to the methods’ admissibility in a judicial process.

show abstract

Section: Methods For Evaluating Dfai Techniquesmentioning

confidence: 99%

Digital Forensics AI: Evaluating, Standardizing and Optimizing Digital Evidence Mining Techniques

Solanke

Biasiotti²

2022

Künstl Intell

View full text Add to dashboard Cite

show abstract

“…648 March 2022 Biometric detection and extraction approaches, in particular, can increase investigatory capacity and enhance CSAM investigations. These tools typically rely on the detection of 'primary' biometric modalities including faces (Macedo, Costa, & dos Santos 2018;Ulges & Stahl 2011) but also use other 'soft' biometric modalities to detect nudity (de Castro Polastro & da Silva Eleuterio 2010;Vitorino et al 2018), skin tones (Islam, Watters & Yearwood 2011;Sae-Bae et al 2014;Yaqub, Mohanty & Memon 2018), and subject age (Gangwar et al 2021;Islam et al 2019).…”

mentioning

confidence: 99%

Developing automated methods to detect and match face and voice biometrics in child sexual abuse videos

Westlake¹,

Brewer²

2022

View full text Add to dashboard Cite

The proliferation of child sexual abuse material (CSAM) is outpacing law enforcement’s ability to address the problem. In response, investigators are increasingly integrating automated software tools into their investigations. These tools can detect or locate files containing CSAM, and extract information contained within these files to identify both victims and offenders. Software tools using biometric systems have shown promise in this area but are limited in their utility due to a reliance on a single biometric cue (namely, the face). This research seeks to improve current investigative practices by developing a software prototype that uses both faces and voices to match victims and offenders across CSAM videos. This paper describes the development of this prototype and the results of a performance test conducted on a database of CSAM. Future directions for this research are also discussed.

show abstract

Computer Vision for Facial Analysis Using Human-Computer Interaction Models

Ren

2021

J. Inter. Net.

View full text Add to dashboard Cite

A facial recognition device is a technology that can be used for authenticating a human face by ID verification and for calculating facial features from a single image using a visual image or a video to a facial database. Computer vision’s main objective enables identifying images, detecting speech, the concentration of attention, facial expressions, and recognition of emotions. Face identification is an important part of the understanding of audiovisual speech. In this paper, Intelligent Schemes for human-computer interaction (IS-HCI) provides a broader and more expressive range of computer-based vision features for processing data from one or more sensors. In particular cases of impairment, alternative interaction methods dependent on computer vision can be effectively modified. Facial identification is a biometric safety category. This paper aims to help technology-based concepts, allowing a child with a debilitating neuromuscular disorder to communicate with the robot by recognizing facial expressions. The proposed model was suggested to test in photographs taken from children’s videos, and the preliminary findings show that computational interactions with children through facial expression would break down barriers to their relationship with machines with people with limited mobility. Thus the experimental results show the proposed method IS-HCI to enhance facial expression and effectively interact with the children to achieve sensitivity (94.12%), specificity (96.84%), recognition rate (94.23%), probability (21.78%), accuracy (96.69%), expression prediction rate (98.14%), muscle activity level (79.84%) compared to other methods.

show abstract

Toward Detection of Child Exploitation Material: A Forensic Approach

Cited by 3 publications

References 20 publications

Digital Forensics AI: Evaluating, Standardizing and Optimizing Digital Evidence Mining Techniques

Digital Forensics AI: Evaluating, Standardizing and Optimizing Digital Evidence Mining Techniques

Developing automated methods to detect and match face and voice biometrics in child sexual abuse videos

Computer Vision for Facial Analysis Using Human-Computer Interaction Models

Contact Info

Product

Resources

About