Detecting illicit drugs on social media using automated social media intelligence analysis (ASMIA)
CSS'12 Proceedings of the 4th international conference on Cyberspace Safety and Security
Detecting malicious behaviour using supervised learning algorithms of the function calls
International Journal of Electronic Security and Digital Forensics
| Hi-index | 0.00 |
Threat of cyber crime is a growing danger to the economy. Industries and businesses are targeted by cyber-criminals along with members of the general public. Since cyber crime is often a symptom of more complex criminological regimes such as laundering, trafficking and terrorism, the true damage caused to society is unknown. Dissimilarities in reporting procedures and non-uniform cyber crime classifications lead international reporting bodies to produce incompatible results which cause difficulties in making valid comparisons. A cyber crime classification framework has been identified as necessary for the development of an inter-jurisdictional, transnational, and global approach to identify, intercept, and prosecute cyber-criminals. Outlined in this paper is a cyber crime classification framework which has been applied to the incidence of scams. Content analysis was performed on over 250 scam descriptions stemming from in excess of 35 scamming categories and over 80 static features derived. Using hierarchical cluster and discriminant function analysis, the sample was reduced from over 35 ambiguous categories into 7 scam types and the top four scamming functions - identified as scamming business processes, revealed. The results of this research bear significant ramifications to the current state of scam and cyber crime classification, research and analysis, as well as offer significant insight into the business processes and applications adopted by scammers and cyber-criminals.