M. Barni
ABSTRACT
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.
- H. L. B. Goethals, S. Laur and T. Mielikainen. On secure scalar product computation for privacy-preserving data mining. In 7th ICISC, 2004.]]Google Scholar
- R. Brinkman, J. M. Doumen, and W. Jonker. Using secret sharing for searching in encrypted data. In Proc. of Workshop on Secure Data Management in a Connected World (SDM 2004), Springer-Verlag LNCS 3178, pages 18--27, 2004.]]Google ScholarCross Ref
- D. Chaum, C. Crépeau, and I. Damgård. Multiparty unconditionally secure protocols. In STOC '88: Proceedings of the twentieth annual ACM symposium on Theory of computing, pages 11--19, New York, NY, USA, 1988. ACM Press.]] Google ScholarDigital Library
- I. Damgård and M. Jurik. A generalisation, a simplification and some applications of paillier's probabilistic public-key system. In Public Key Cryptography, pages 119--136, 2001.]] Google ScholarDigital Library
- W. Du and M. J. Atallah. Privacy-preserving statistical analysis. In Proceedings of the 17th Annual Computer Security Applications Conference, pages 102--110, New Orleans, Louisiana, USA, December 10-14 2001.]] Google ScholarDigital Library
- O. Goldreich, S. Micali, and A. Wigderson. How to play any mental game or a completeness theorem for protocols with honest majority. In STOC, pages 218--229. ACM, 1987.]] Google ScholarDigital Library
- G. Jagannathan, K. Pillaipakkamnatt, and R. Wright. A new privacy-preserving distributed k-clustering algorithm. In 2006 SIAM International Conference on Data Mining (SDM, Bethesda, Maryland, April 20-22 2006.]]Google ScholarCross Ref
- M. Johnson, P. Ishwar, V. Prabhakaran, D. Schonberg, and K. Ramchandran. On compressing encrypted data. IEEE Trans. on Signal Processing, 52(10):2992--3006, October 2004.]]Google ScholarDigital Library
- M. Naor and B. Pinkas. Oblivious transfer and polynomial evaluation. In 31th Annual Symposium on Theory of Computer Science (STOC), pages 245--254, Atlanta, GA, May 1-4 1999.]] Google ScholarDigital Library
- P. Pailler. Public-key cryptosystems based on composite degree residuosity classes. In Proceedings of Eurocrypt'99, Lecture Notes is Computer Science vol. 1592, pages 223--238. Springer-Verlag, 1999.]]Google Scholar
- P. Ravikumar, W. Cohen, and S. Fienberg. A secure protocol for computing string distance metrics. In Workshop on Privacy and Security Aspects of Data Mining, Brighton, UK, November 1 2004.]]Google Scholar
- D. X. Song, D. Wagner, and A. Perrig. Practical techniques for searches on encrypted data. In Proceedings of the 2000 IEEE symposium on Security and Privacy (S&P 2000), 2000.]] Google ScholarDigital Library
- W. Du and M. J. Atallah. Privacy-preserving cooperative scientific computations. In 14th IEEE Computer Security Foundations Workshop, pages 273--282, Nova Scotia, Canada, June 11-13 2001.]] Google ScholarDigital Library
- R. Wright and Z. Yang. Privacy-preserving bayesian network structure computation on distributed heterogeneous data. In KDD'04: Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, pages 713--718, New York, NY, USA, 2004. ACM Press.]] Google ScholarDigital Library
- A. C. Yao. Protocols for secure computations. In Proceedings of Twenty-third IEEE Symposium on Foundations of Computer Science, pages 160--164, Chicago, Illinois, November 1982.]]Google ScholarCross Ref
Index Terms
- A privacy-preserving protocol for neural-network-based computation
Recommendations
Privacy-preserving backpropagation neural network learning
With the development of distributed computing environment, many learning problems now have to deal with distributed input data. To enhance cooperations in learning, it is important to address the privacy concern of each data holder by extending the ...
An Efficient 3-Party Framework for Privacy-Preserving Neural Network Inference
Computer Security – ESORICS 2020Privacy Leakage in Privacy-Preserving Neural Network Inference
Computer Security – ESORICS 2022AbstractThe community has seen many attempts to secure machine learning algorithms from multi-party computation or other cryptographic primitives. An interesting 3-party framework (SCSDF hereafter) for privacy-preserving neural network inference was ...
Comments