IRI: a quantitative aproach to inference analysis in relational databases

摘要

A new approach is introduced to evaluate inference risks in element-levle labelling relational databases.Techniques form rough set theory are used to capture the sematntic s of data and a quantitative measrure Inference Risk Index (IRI) has been defined to characteruise possible inference risks due to material implicatoions reflected by the data.The apporach is hsown to be able to take into account of all certain and possible material imlplications in the data,including functioal dependencies.It can aalso be used to address inference threats posed by rule-induction techniuqe s form data mining.A major advantage of our approach is that the quantitiative measrue IRI is ocmputed directly form data wthout knowledge input from System Security Officer.the computation is efficient and allows for real-time monitoring of inference risks during database run time,Therefore,we are able to follow the changes in data patterns during database lifetime.