ABSTRACT :
Despite the rapid escalation of cyber threats, there has still been little research into the foundations of the subject or methodologies that could serve to guide Information Systems researchers and practitioners who deal with cybersecurity. In addition, little is known about Crime-as-a-Service (CaaS), a criminal business model that underpins the cybercrime underground. This research gap and the practical cybercrime problems we face have motivated us to investigate the cybercrime underground economy by taking a data analytics approach from a design science perspective. To achieve this goal, we propose (1) a data analysis framework for analysing the cybercrime underground, (2) CaaS and crimeware definitions, and (3) an associated classification model. In addition, we (4) develop an example application to demonstrate how the proposed framework and classification model could be implemented in practice. We then use this application to investigate the cybercrime underground economy by analysing a large dataset obtained from the online hacking community. By taking a design science research approach, this study contributes to the design artifacts, foundations, and methodologies in this area. Moreover, it provides useful practical insights to practitioners by suggesting guidelines as to how governments and organizations in all industries can prepare for attacks by the cybercrime underground.
EXISTING SYSTEM :
the practical implications of this study mainly affect the capable guardians against crime, because our results indicate how underground attackers perceive preventive measures. A previous review of the current status of legal, organizational, and technological efforts to combat cybercrime in different countries relied on a case study of the work being done in Taiwan [64]. It made four recommendations for governments, lawmakers, international organizations, intelligence and law enforcement agencies, and researchers: (1) regularly update existing laws; (2) enhance specialized task forces; (3) use civil resources; and (4) promote cybercrime research. The practical implications of our study are based on those of the previous study [64]. We have already discussed the fourth recommendation (“promote cybercrime research”) in the previous section, so we will now focus on the other three areas
PROPOSED SYSTEM :
To be classified as a dangerous Threat, for example, a message must also contain Market-related keywords. Messages containing both Threat- and Market-related keywords are considered more dangerous (e.g., “Selling silent Microsoft Office exploit”) than messages with only Threat-related keywords (e.g., “Can I hide a file inside a word doc?”). Likewise, messages related to the Product/Service, Market, and File Extension categories are not identified as dangerous if they only contain keywords related to one category. In addition, messages containing Exclusion-related keywords (e.g., “tutorials” or “tips”) are not identified as a dangerous (see Fig. 2). To classify messages correctly, we also use keywords related to CaaS and crimeware. This classification step is applied after the messages have been filtered as above, so many keywords are not needed and the criteria are simpler. However, when a message fits into multiple categories, this overlap is recorded so as to derive additional insights from the later analysis and applications.
SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10
HARDWARE REQUIREMENTS:
Processor : Core I3
RAM Capacity : 2 GB
Hard Disk : 250 GB
Monitor : 15″ Color
Mouse : 2 or 3 Button Mouse
Key Board : Windows 08/10
