Privacy Preserving Back-Propagation Neural Network Learning Made Practical with Cloud Computing

By Jiawei Yuan, Shucheng Yu. 2014

245 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Federated Machine Learning (2019, neutral): “Recent works adopted homomorphic encryption for centralizing and training data on cloud [75, 76].”
Learning Anonymized Representations with Adversarial Neural Networks (2018, background): “[Chen and Zhong, 2009] and [Yuan and Yu, 2014] presented a privacy-preserving distributed algorithm of backpropagation which allows a neural network to be trained without requiring either party to reveal her data to the other.”
Federated Learning: Challenges, Methods, and Future Directions (2019, methodology): “n be used to secure the learning process by computing on encrypted data, although it has currently been applied in limited settings, e.g., training linear models [82] or involving only a few entities [133]. When the sensitive datasets are distributed across different data owners, another natural opt”
Privacy Preserving Machine Learning with Homomorphic Encryption and Federated Learning (2021, background): “As a multi-party cooperative machine learning, federated learning has gradually attracted much attention in research and industry [32,33].”
Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinator (2019, methodology): “…plaintext, we have: In some recent works, raw data from different parties are encrypted with AHE and then uploaded to a central server (e.g. a cloud host), and models are learned over the encrypted data by running machine learning algorithms adapted for AHE [Aono et al., 2016; Yuan and Yu, 2014].”
Privacy-preserving outsourced classification in cloud computing (2017, background): “Yuan et al. [16] adopted the BGN ‘doubly homomorphic’ encryption [17] to support ﬂexible operations over ciphertexts, and realized a privacy-preserving back-propagation algorithm.”
Privacy-Preserving Machine Learning Algorithms for Big Data Systems (2015, methodology): “For example, in [30], Yuan and Yu use homomorphic encryption to calculate the delta function in the back-propagation training; in [28] and [31], Jiang and Zhan propose to use secure dot product protocols and secure sum protocols to get the kernel matrix in SVM learning; in [20], Lindell and Pinkas p”
A Scalable Approach for Privacy-Preserving Collaborative Machine Learning (2020, background): “The first one is Homomorphic Encryption (HE) [15], which enables computations on encrypted data, and has been applied to privacy-preserving machine learning [16, 20, 17, 41, 24, 22, 38, 19].”
Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption (2017, background): “The homomorphic cryptosystems also enable a variety of privacy-preserving machine learning and data mining [7, 16, 26, 42, 48, 49, 60, 63, 67] because they can make some parameters perfectly secret by encrypting them.”
Data-intensive applications, challenges, techniques and technologies: A survey on Big Data (2014, background): “The other one is to scale up neural networks in parallel and distributed ways [119,40,9,202].”
A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection (2019, methodology): “[179]. Here we introduce two major approaches that are adopted in current FLSs for data protection: cryptographic methods and differential privacy. Cryptographic methods such as homomorphic encryption[15, 77, 27, 33, 74, 145, 146, 204, 206, 112], and secure multi-party computation (SMC) [157, 36, 23”
Privacy Preserving Deep Computation Model on Cloud for Big Data Feature Learning (2016, methodology): “pants by using the power of cloud computing [21].”