Fault tolerant secure K-means clustering data mining on semi-honest parties
This project report will discuss the design of secure fault tolerant k-means clustering data mining on semi-honest parties. The algorithm will protect all parties’ privacy while using caching and checkpointing to tolerate unexpected fault exceptions, such as party dies during processing. Sha...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
2010
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/36286 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Summary: | This project report will discuss the design of secure fault tolerant k-means clustering data mining on semi-honest parties. The algorithm will protect all parties’ privacy while using caching and checkpointing to tolerate unexpected fault exceptions, such as party dies during processing.
Shair Secret Sharing Scheme and Secure Scalar Product will be used to maintain caching data. The algorithm fault tolerance threshold is (k, N), which means up to N-k parties dying is tolerable. Other different types of faults are also handled using different ways. |
---|