چکیده:
Nowadays, World Wide Web has become a popular medium to search information, business, trading and so on. Various organizations and companies are also employing the web in order to introduce their products or services around the world. Therefore E-commerce or electronic commerce is formed. E-commerce is any type of business or commercial transaction that involves the transfer of information across the internet. In this situation a huge amount of information is generated and stored in the web services. This information overhead leads to difficulty in finding relevant and useful knowledge, therefore web mining is used as a tool to discover and extract the knowledge from the web. Beside, the security issues are the most precious problems in every electronic commercial process. This massive increase in the uptake of ecommerce has led to a new generation of associated security threats. In this paper we use web mining techniques for security purposes, in detecting, preventing and predicting cyber attacks on virtual space.
خلاصه ماشینی:
In this paper we use web mining techniques for security purposes, in detecting, preventing and predicting cyber attacks on virtual space.
These techniques apply log files and other traffic information that being generated and stored automatically on web servers.
Therefore log files provide an easy available and process features for security issues (Marchany & Tront , 2002) There are two different strategies for attacks detection.
Web usage mining is the way to find out the interests of web users, by analysis of the visitor's interactions (Masseglia, Tanasa & Trousse ,2007) Web usage mining applies the traffic information of web servers log files and other relational data bases, as the input of data mining techniques, such as association rules, path analysis, clustering and classification.
In this paper we focus on web usage mining because we want to use this type of knowledge to detecting, predicting and prevention of security threats.
In pattern discovery stage, we use statistical techniques, data base, data mining, machine learning and pattern recognition on transaction log files to extract hidden patterns and behavior of the visitors.
The tools applied for this phase use techniques based on AI (Artificial Intelligence), data mining algorithms, psychology and information theory.
4. Web usage mining can be a significant technique to Fraud Detection and finding unusual accesses to secure data and transactions in any electronic interaction.
Therefore, we can benefit from web data mining to identification, prevention and prediction various cyber attacks that might be occurred for our e-commerce website.