Privacy Preserving Multi-party Machine Learning with Homomorphic Encryption
نویسندگان
چکیده
Privacy preserving multi-party machine learning approaches enable multiple parties to train a machine learning model from aggregate data while ensuring the privacy of their individual datasets is preserved. In this paper, we propose a privacy preserving multi-party machine learning approach based on homomorphic encryption where the machine learning algorithm of choice is deep neural networks. We develop theoretical foundation for implementing deep neural networks over encrypted data and utilize it in developing efficient and practical algorithms in encrypted domain.
منابع مشابه
Privacy Preserving PageRank Algorithm By Using Secure Multi-Party Computation
In this work, we study the problem of privacy preserving computation on PageRank algorithm. The idea is to enforce the secure multi party computation of the algorithm iteratively using homomorphic encryption based on Paillier scheme. In the proposed PageRank computation, a user encrypt its own graph data using asymmetric encryption method, sends the data set into different parties in a privacy-...
متن کاملOptimized Two Party Privacy Preserving Association Rule Mining Using Fully Homomorphic Encryption
In two party privacy preserving association rule mining, the issue to securely compare two integers is considered as the bottle neck to achieve maximum privacy. Recently proposed fully homomorphic encryption (FHE) scheme by Dijk et.al. can be applied in secure computation. Kaosar, Paulet and Yi have applied it in preserving privacy in two-party association rule mining, but its performance is no...
متن کاملPrivacy-Preserving Distributed Data Mining Techniques: A Survey
In various distributed data mining settings, leakage of the real data is not adequate because of privacy issues. To overcome this problem, numerous privacy-preserving distributed data mining practices have been suggested such as protect privacy of their data by perturbing it with a randomization algorithm and using cryptographic techniques. In this paper, we review and provide extensive survey ...
متن کاملProtocol Design for Privacy-Preserving Data Mining Using Partial Homomorphic Encryption
With the advance of computing power, data mining techniques can extract useful information from large amount of data. In 2012, 2.5 quintillion bytes of data (1 follow 18 zeroes) are created every day. Data privacy is of utmost concern for distributed data mining across multiple parties, which may be competitors. In this thesis, we focus on the privacy preserving techniques in distributed data m...
متن کاملPrivacy-Preserving Clustering Using Representatives over Arbitrarily Partitioned Data∗
The challenge in privacy-preserving data mining is avoiding the invasion of personal data privacy. Secure computation provides a solution to this problem. With the development of this technique, fully homomorphic encryption has been realized after decades of research; this encryption enables the computing and obtaining results via encrypted data without accessing any plaintext or private key in...
متن کامل