STOC '87 Proceedings of the nineteenth annual ACM symposium on Theory of computing
Multiparty unconditionally secure protocols
STOC '88 Proceedings of the twentieth annual ACM symposium on Theory of computing
Oblivious transfer and polynomial evaluation
STOC '99 Proceedings of the thirty-first annual ACM symposium on Theory of computing
Privacy-Preserving Cooperative Statistical Analysis
ACSAC '01 Proceedings of the 17th Annual Computer Security Applications Conference
Privacy-Preserving Cooperative Scientific Computations
CSFW '01 Proceedings of the 14th IEEE workshop on Computer Security Foundations
Practical Techniques for Searches on Encrypted Data
SP '00 Proceedings of the 2000 IEEE Symposium on Security and Privacy
Privacy-preserving Bayesian network structure computation on distributed heterogeneous data
Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
Public-key cryptosystems based on composite degree residuosity classes
EUROCRYPT'99 Proceedings of the 17th international conference on Theory and application of cryptographic techniques
IEEE Transactions on Signal Processing - Part II
Oblivious neural network computing via homomorphic encryption
EURASIP Journal on Information Security
Privacy-preserving backpropagation neural network learning
IEEE Transactions on Neural Networks
Secure two and multi-party association rule mining
CISDA'09 Proceedings of the Second IEEE international conference on Computational intelligence for security and defense applications
Privacy-preserving back-propagation and extreme learning machine algorithms
Data & Knowledge Engineering
Hi-index | 0.00 |
The problem of secure data processing by means of a neural network (NN) is addressed. Secure processing refers to the possibility that the NN owner does not get any knowledge about the processed data since they are provided to him in encrypted format. At the same time, the NN itself is protected, given that its owner may not be willing to disclose the knowledge embedded within it. Two different levels of protection are considered: according to the first one only the NN weights are protected, whereas the second level also permits to protect the node activation functions. An efficient way of implementing the proposed protocol by means of some recently proposed multi-party computation techniques is described.