Here, we propose data mining approach for database intrusion detection. In each database, there are a few attributes or columns that are more important or sensitive to be tracked or sensed for malicious modifications as compared to the other attributes. Our approach concentrates on mining pre-write as well as post-write data dependencies among the important or sensitive data items in relational database. By data dependency we refer to the data access correlations between two or more data items. These dependencies are generated in the form of association rules i.e. before one data item is updated in the data base what other data items probably need to be read or write and after this data item is updated what other data items are most likely to be updated by the same transaction. Any transaction that does not follow these dependency rules are identified as malicious. We also suggest removal of redundant rules in our proposed algorithm to minimize the number of comparisons during detection phase. We compare our proposed approach with existing approach on various performance evaluation metrics and analyze the results

Jay Kant Pratap Singh Yadav Completed his B.Tech(Computer Science & Engineering), M.Tech (Computer Engineering) from Sardar Vallabhbhai National Institute of Technology,Surat(India). He has about 13 years teaching experience in various technical colleges of india. His research interest is in Machine Learning,Soft Computing,Data Mining .