期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2007
卷号：7
期号：8
页码：258-266
出版社：International Journal of Computer Science and Network Security
摘要：Knowledge is supremacy and the more knowledgeable we are about information break-in, we are less prone to fall prey to the evil hacker sharks of information technology. The information technology is perpetually emerging and we are all beyond doubt minuscule gravels in a cosmic marine of information. Knowledge is pre-eminence, but as humble users of the most modern technologies we are pitted with possessions that may even make us paranoid concerning usage of a computer. Don’t be discouraged though, as we will tell the techniques to protect ourselves while we are reaching an accord. Privacy preserving data mining (i.e., is accomplishing valid data mining results devoid of the wisdom of the core data values) has been receiving attentiveness in the research society and beyond.Reaching a pact is defined as negotiation and the process ends in a ultimate contract between the participating parties. Automated Negotiation uses a wide variety of machine learning techniques.One foremost hindrance in automated negotiation is incorporating acumen into a computer system that carries out a negotiation [11], thus enabling the negotiation system to carry out automated negotiations efficiently and shrewdly on behalf of its clients. This paper presents an idea about the privacy preserving negotiation that is performed between individuals dealing with negotiating databases of users. It uses association rules and entropy discretization.As the BIRCH algorithms performance is extensive in terms of memory requirements, run time, clustering quality, stability and scalability it is used for data clustering and merging the data without disclosing the private and sensitive details of the user’s data. The sensitive data are protected from the other user by using a protocol defined. It has lower communication complexity secure protocol; it will not disclose the private data’s of the parties participating and it resists some degree of conspiracy and malevolent attacks. Entropy gives the information required in bits. After splitting of data, the insensitive data are fused and the results are obtained. This negotiation presented is of high order by using a low communication protocol between the users. The protocol used for the negotiation process provides the definite rules and conditions for merging the data tables.
关键词：BIRCH(Balanced Iterative Reducing and Clustering using Hierarchies), Clustering, Entropy-based Splitting, Negotiation
