In recent years, there is an increase in the geographical and logical spread of data. Even the organizations competing with each other normally, increasingly collaborate with each other to exploit the distributed data and collaboratively undertake data mining therein. However, the increased sharing of data gives rise to privacy concerns as the collaborative entities may be competing with each other. The need for efficient algorithms in terms of privacy and efficiency for the different adversary and data models for various areas of application is therefore an important research problem. In this chapter, we discuss the state-of-the-art of cryptographic Privacy Preserving Distributed Data Mining (PPDDM) approaches. In particular, we focus on the case study of Privacy Preservation in Distributed Association Rule Mining (PPDARM). We primarily discuss information-theoretically secure schemes that aim to improve the state-of-the-art in the area of PPDARM by providing the highest level of security.We discuss efficient and secure privacy preserving information-theoretically secure schemes that an application designer could choose from depending on the application requirements, the partition model, the adversary model and the number of participating parties for collaborative association rule mining.
Weitere Kapitel dieses Buchs durch Wischen aufrufen
Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten
Sie möchten Zugang zu diesem Inhalt erhalten? Dann informieren Sie sich jetzt über unsere Produkte:
- Information-Theoretically Secure Privacy Preserving Approaches for Collaborative Association Rule Mining
Nirali R. Nanavati
Devesh C. Jinwala
- Chapter 4