Digital Forensics and Cyber Crime. First International ICST Conference, ICDF2C 2009, Albany, NY, USA, September 30-October 2, 2009, Revised Selected Papers

Research Article

Detecting and Preventing the Electronic Transmission of Illicit Images and Its Network Performance

Download
386 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-11534-9_14,
        author={Amin Ibrahim and Miguel Martin},
        title={Detecting and Preventing the Electronic Transmission of Illicit Images and Its Network Performance},
        proceedings={Digital Forensics and Cyber Crime. First International ICST Conference, ICDF2C 2009, Albany, NY, USA, September 30-October 2, 2009, Revised Selected Papers},
        proceedings_a={ICDF2C},
        year={2012},
        month={5},
        keywords={Computer forensics network monitoring image classification feature extraction pattern recognition Netfilter network overhead},
        doi={10.1007/978-3-642-11534-9_14}
    }
    
  • Amin Ibrahim
    Miguel Martin
    Year: 2012
    Detecting and Preventing the Electronic Transmission of Illicit Images and Its Network Performance
    ICDF2C
    Springer
    DOI: 10.1007/978-3-642-11534-9_14
Amin Ibrahim1,*, Miguel Martin1,*
  • 1: University of Ontario Institute of Technology
*Contact email: amin.ibrahim@uoit.ca, miguel.vargas-martin@uoit.ca

Abstract

Child exploitation through the use of the Internet as a delivery and exchange tool is a growing method of abuse towards children. It is shown that a Stochastic Learning Weak Estimator learning algorithm and a Maximum Likelihood Estimator learning algorithm can be applied against Linear Classifiers to identify and filter illicit pornographic images. In this paper, these two learning algorithms were combined with distance algorithms such as the Non-negative Vector Similarity Coefficient-based Distance algorithm, Euclidian Distance, and a Weighted Euclidian Distance algorithm. Experimental results showed that classification accuracies and the network overhead did have a significant effect on routing devices.