ABSTRACT
We give efficient protocols for secure and private k-nearest neighbor (k-NN) search, when the data is distributed between two parties who want to cooperatively compute the answers without revealing to each other their private data. Our protocol for the single-step k-NN search is provably secure and has linear computation and communication complexity. Previous work on this problem had a quadratic complexity, and also leaked information about the parties' inputs. We adapt our techniquesto also solve the general multi-step k-NN search, and describe a specific embodiment of it for the case of sequence data. The protocols and correctness proofs can be extended to suit other privacy-preserving data mining tasks, such as classification and outlier detection.
Recommendations
Efficient Privacy-preserving Non-exhaustive Nearest Neighbor Search of large-scale databases
AbstractThe Nearest Neighbor Search is a process allowing a query owner to learn the nearest neighbor of his query in a database. Nearest Neighbor Search serves an essential role in a variety of applications of similarity search. A useful ...
Compacting privacy-preserving k-nearest neighbor search using logic synthesis
DAC '15: Proceedings of the 52nd Annual Design Automation ConferenceThis paper introduces the first efficient, scalable, and practical method for privacy-preserving k-nearest neighbors (k-NN) search. The approach enables performing the widely used k-NN search in sensitive scenarios where none of the parties reveal their ...
Order preserving hashing for approximate nearest neighbor search
MM '13: Proceedings of the 21st ACM international conference on MultimediaIn this paper, we propose a novel method to learn similarity-preserving hash functions for approximate nearest neighbor (NN) search. The key idea is to learn hash functions by maximizing the alignment between the similarity orders computed from the ...
Comments