A privacy-preserving protocol for neural-network-based computation

By Mauro Barni, Claudio Orlandi, Alessandro Piva. 2006

153 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

Secure Evaluation of Quantized Neural Networks (2019, methodology): “Secure evaluation of Neural Networks can be traced back to at least the work by Orlandi et al. [5, 51] which present a solution based on HE techniques.”
Distributed learning of deep neural network over multiple agents (2018, background): “Under distributed and secure processing paradigms, the owner of the neural network doesn’t have access to the actual raw data used to train the neural network [21].”
DeepSecure: Scalable Provably-Secure Deep Learning (2017, methodology): “To address the issue of information leakage as a result of sharing the intermediate results, [24] and [25] enhance the protocol initially proposed in [23] to obscure the weights.”
EPIC: Efficient Private Image Classification (or: Learning from the Masters) (2019, methodology): “Unlike previous work [4,5,20], we can fully outsource the task at hand, in such a way that the classification algorithm provider does not need to be the same entity as the cloud computing provider.”
High Accuracy and High Fidelity Extraction of Neural Networks (2019, methodology): “A practical approach is secure multiparty computation, where each query is computed by running a protocol between the model owner and querier [57].”
Privacy-Preserving Classification on Deep Neural Network (2017, background): “In 2006, Barni et al [2] proposed a privacy preserving neural network classification algorithm based on secure multi-party computation and homomorphic encryption.”
Secure Outsourced Matrix Computation and Application to Neural Networks (2018, unknown): “The second scenario was considered by Makri et al. [35] based on Multi-Party Computation (MPC) using polynomial kernel support vector machine classification.”
Security and Privacy Issues in Deep Learning (2018, background): “] Papernot et al. [25] Xie et al. [94] Phan et al. [95] Papernot et al. [26] McMahan et al. [27] Phan et al. [96] Triastcyn and Faltings [97] Phan et al. [98] Secure Multi-Party Training Barni et al. [99] Orlandi et al. [100] Shokri and Shmatikov [29] Liu et al. [101] Liu et al. [102] Mohassel and Z”
Towards Deep Neural Network Training on Encrypted Data (2019, background): “An early work along these lines is due to Barni et al. and Orlandi et al. [2, 25], that combined additively-homomorphic encryption with an interactive protocol, and were able to run the inference part of a small network in about ten seconds.”
High-Fidelity Extraction of Neural Network Models (2019, background): “A more realizable approach is secure multiparty computation, where the model owner and querying party run a protocol for each query to the model [56].”
Privacy-Preserving Backpropagation Neural Network Learning (2009, background): “However, in terms of multi-layer neural networks, their protocol is limited as it is only for one simple neural network conﬁguration with one node in the output layer and no hidden layers.”
XONN: XNOR-based Oblivious Deep Neural Network Inference (2019, methodology): “on of the GC protocol. All of the parameter adjustments are also automatically performed by the compiler. 5 Related Work One of the early solutions for oblivious inference is proposed by Barni et al. [38] that leverages homomorphic encryption. Howerver, this work leaks some information about the int”
Oblivious Neural Network Computing via Homomorphic Encryption (2007, background): “Previous works on privacy preserving NN computing are limited to the systems presented in [8, 17].”
CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy (2016, methodology): “Barni et al. (2006) presented a method of this type, where the data owner encrypts the data and sends it to the cloud.”
A privacy-preserving algorithm for distributed training of neural network ensembles (2012, unknown): “, [25]) on privacy-preserving neural networks.”