Designing privacy-preserving interval operations based on homomorphic encryption and secret sharing techniques

2017 ◽  
Vol 25 (1) ◽  
pp. 59-81 ◽  
Author(s):  
Stefan Wüller ◽  
Daniel Mayer ◽  
Fabian Förg ◽  
Samuel Schüppen ◽  
Benjamin Assadsolimani ◽  
...  
Keyword(s):  
Secret Sharing ◽  
Homomorphic Encryption ◽  
Privacy Preserving

Analysis and Evaluation of Novel Privacy Preserving Techniques for Collaborative Temporal Association Rule Mining Using Secret Sharing

2014 ◽  
Vol 5 (3) ◽  
pp. 58-76 ◽  
Author(s):  
Nirali R. Nanavati ◽  
Neeraj Sen ◽  
Devesh C. Jinwala
Keyword(s):  
Secret Sharing ◽  
Association Rule ◽  
Association Rule Mining ◽  
Homomorphic Encryption ◽  
Privacy Preserving ◽  
Experimental Results ◽  
Public Key ◽  
Secret Sharing Scheme ◽  
Rule Mining ◽  
Sharing Scheme

With digital data being abundant in today's world, competing organizations desire to gain insights about the market, without putting the privacy of their confidential data at risk. This paper provides a new dimension to the problem of Privacy Preserving Distributed Association Rule Mining (PPDARM) by extending it to a distributed temporal setup. It proposes extensions of public key based and non-public key based additively homomorphic techniques, based on efficient private matching and Shamir's secret sharing, to privately decipher these global cycles in cyclic association rules. Along with the theoretical analysis, it presents experimental results to substantiate it. This paper observes that the Secret Sharing scheme is more efficient than the one based on Paillier homomorphic encryption. However, it observes a considerable increase in the overhead associated with the Shamir's secret sharing scheme, as a result of the increase in the number of parties. To reduce this overhead, it extends the secret sharing scheme without mediators to a novel model with a Fully Trusted and a Semi Trusted Third Party. The experimental results establish this functioning for global cycle detections in a temporal setup as a case study. The novel constructions proposed can also be applied to other scenarios that want to undertake Secure Multiparty Computation (SMC) for PPDARM.

scholarly journals Privacy Preserving Implementation of the Max-Sum Algorithm and its Variants

2017 ◽  
Vol 59 ◽  
pp. 311-349 ◽  
Author(s):  
Tamir Tassa ◽  
Tal Grinshpoun ◽  
Roie Zivan
Keyword(s):  
Secret Sharing ◽  
Privacy Preservation ◽  
Homomorphic Encryption ◽  
Privacy Preserving ◽  
Factor Graph ◽  
Multiple Agents ◽  
Ongoing Effort

One of the basic motivations for solving DCOPs is maintaining agents' privacy. Thus, researchers have evaluated the privacy loss of DCOP algorithms and defined corresponding notions of privacy preservation for secured DCOP algorithms. However, no secured protocol was proposed for Max-Sum, which is among the most studied DCOP algorithms. As part of the ongoing effort of designing secure DCOP algorithms, we propose P-Max-Sum, the first private algorithm that is based on Max-Sum. The proposed algorithm has multiple agents preforming the role of each node in the factor graph, on which the Max-Sum algorithm operates. P-Max-Sum preserves three types of privacy: topology privacy, constraint privacy, and assignment/decision privacy. By allowing a single call to a trusted coordinator, P-Max-Sum also preserves agent privacy. The two main cryptographic means that enable this privacy preservation are secret sharing and homomorphic encryption. In addition, we design privacy-preserving implementations of four variants of Max-Sum. We conclude by analyzing the price of privacy in terns of runtime overhead, both theoretically and by extensive experimentation.

scholarly journals Privacy Preserving Machine Learning with Homomorphic Encryption and Federated Learning

2021 ◽  
Vol 13 (4) ◽  
pp. 94
Author(s):  
Haokun Fang ◽  
Quan Qian
Keyword(s):  
Machine Learning ◽  
Homomorphic Encryption ◽  
Privacy Preserving ◽  
Great Success ◽  
Learning Framework ◽  
Computational Overhead ◽  
Important Concern ◽  
Speed Up ◽  
Key Length ◽  
Core Idea

Privacy protection has been an important concern with the great success of machine learning. In this paper, it proposes a multi-party privacy preserving machine learning framework, named PFMLP, based on partially homomorphic encryption and federated learning. The core idea is all learning parties just transmitting the encrypted gradients by homomorphic encryption. From experiments, the model trained by PFMLP has almost the same accuracy, and the deviation is less than 1%. Considering the computational overhead of homomorphic encryption, we use an improved Paillier algorithm which can speed up the training by 25–28%. Moreover, comparisons on encryption key length, the learning network structure, number of learning clients, etc. are also discussed in detail in the paper.

Sign in / Sign up

Export Citation Format

Share Document