scholarly journals Fully Homomorphically Encrypted Deep Learning as a Service

2021 ◽  
Vol 3 (4) ◽  
pp. 819-834
Author(s):  
George Onoufriou ◽  
Paul Mayfield ◽  
Georgios Leontidis
Keyword(s):  
Deep Learning ◽  
Data Privacy ◽  
Homomorphic Encryption ◽  
Percentage Error ◽  
Polynomial Equations ◽  
Fully Homomorphic Encryption ◽  
Sequence Prediction ◽  
Recent Advancement ◽  
Complexity Cost ◽  
Made In

Fully Homomorphic Encryption (FHE) is a relatively recent advancement in the field of privacy-preserving technologies. FHE allows for the arbitrary depth computation of both addition and multiplication, and thus the application of abelian/polynomial equations, like those found in deep learning algorithms. This project investigates how FHE with deep learning can be used at scale toward accurate sequence prediction, with a relatively low time complexity, the problems that such a system incurs, and mitigations/solutions for such problems. In addition, we discuss how this could have an impact on the future of data privacy and how it can enable data sharing across various actors in the agri-food supply chain, hence allowing the development of machine learning-based systems. Finally, we find that although FHE incurs a high spatial complexity cost, the run time is within expected reasonable bounds, while allowing for absolutely private predictions to be made, in our case for milk yield prediction with a Mean Absolute Percentage Error (MAPE) of 12.4% and an accuracy of 87.6% on average.

Secure Two-Party Association Rule Mining Based on One-Pass FP-Tree

2013 ◽  
pp. 82-102
Author(s):  
Golam Kaosar ◽  
Xun Yi
Keyword(s):  
Association Rules ◽  
Association Rule ◽  
Association Rule Mining ◽  
Data Privacy ◽  
Homomorphic Encryption ◽  
Secure Computation ◽  
Rule Mining ◽  
Fully Homomorphic Encryption ◽  
Popular Method ◽  
Tree Method

Frequent Path tree (FP-tree) is a popular method to compute association rules and is faster than Apriori-based solutions in some cases. Association rule mining using FP-tree method cannot ensure entire privacy since frequency of the itemsets are required to share among participants at the first stage. Moreover, FP-tree method requires two scans of database transactions which may not be the best solution if the database is very large or the database server does not allow multiple scans. In addition, one-pass FP-tree can accommodate continuous or periodically changing databases without restarting the process as opposed to a regular FP-tree based solution. In this paper, the authors propose a one-pass FP-tree method to perform association rule mining without compromising any data privacy among two parties. A fully homomorphic encryption system over integer numbers is applied to ensure secure computation among two data sites without disclosing any number belongs to themselves.

scholarly journals Deep Learning Data Privacy Protection Based on Homomorphic Encryption in AIoT

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Yichuan Wang ◽  
Xiaolong Liang ◽  
Xinhong Hei ◽  
Wenjiang Ji ◽  
Lei Zhu
Keyword(s):  
Deep Learning ◽  
Classification Accuracy ◽  
Privacy Protection ◽  
Data Privacy ◽  
Homomorphic Encryption ◽  
Accuracy Rate ◽  
Learning Network ◽  
Shared Data ◽  
Data Privacy Protection ◽  
Deep Learning Network

With the rapid development of 5G technology, its high bandwidth, high reliability, low delay, and large connection characteristics have opened up a broader application field of IoT. Moreover, AIoT (Artificial Intelligence Internet of Things) has become the new development direction of IoT. Through deep learning of real-time data provided by the Internet of Things, AI can judge user habits more accurately, make devices behave in line with user expectations, and become more intelligent, thus improving product user experience. However, in the process, there is a lot of data interaction between the edge and the cloud. Given that the shared data contain a large amount of private information, preserving information security on the shared data is an important issue that cannot be neglected. In this paper, we combine deep learning with homomorphic encryption algorithm and design a deep learning network model based on secure multiparty computing (MPC). In the whole process, we realize that the cloud only owns the encryption samples of users, and users do not own any parameters or structural information related to the model. In the experimental part, we input the encrypted Mnist and Cifar-10 datasets into the model for testing, and the results show that the classification accuracy rate of the encrypted Mnist can reach 99.21%, which is very close to the result under plaintext. The classification accuracy rate of encrypted Cifar-10 can reach 91.35%, slightly lower than the test result in plaintext and better than the existing deep learning network model that can realize data privacy protection.

scholarly journals An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification

2021 ◽  
Vol 13 (11) ◽  
pp. 2221
Author(s):  
Munirah Alkhelaiwi ◽  
Wadii Boulila ◽  
Jawad Ahmad ◽  
Anis Koubaa ◽  
Maha Driss
Keyword(s):  
Deep Learning ◽  
Data Privacy ◽  
Satellite Images ◽  
Homomorphic Encryption ◽  
Satellite Image ◽  
Privacy Preserving ◽  
Cloud Services ◽  
Encryption Scheme ◽  
Privacy Concerns ◽  
Efficient Approach

Satellite images have drawn increasing interest from a wide variety of users, including business and government, ever since their increased usage in important fields ranging from weather, forestry and agriculture to surface changes and biodiversity monitoring. Recent updates in the field have also introduced various deep learning (DL) architectures to satellite imagery as a means of extracting useful information. However, this new approach comes with its own issues, including the fact that many users utilize ready-made cloud services (both public and private) in order to take advantage of built-in DL algorithms and thus avoid the complexity of developing their own DL architectures. However, this presents new challenges to protecting data against unauthorized access, mining and usage of sensitive information extracted from that data. Therefore, new privacy concerns regarding sensitive data in satellite images have arisen. This research proposes an efficient approach that takes advantage of privacy-preserving deep learning (PPDL)-based techniques to address privacy concerns regarding data from satellite images when applying public DL models. In this paper, we proposed a partially homomorphic encryption scheme (a Paillier scheme), which enables processing of confidential information without exposure of the underlying data. Our method achieves robust results when applied to a custom convolutional neural network (CNN) as well as to existing transfer learning methods. The proposed encryption scheme also allows for training CNN models on encrypted data directly, which requires lower computational overhead. Our experiments have been performed on a real-world dataset covering several regions across Saudi Arabia. The results demonstrate that our CNN-based models were able to retain data utility while maintaining data privacy. Security parameters such as correlation coefficient (−0.004), entropy (7.95), energy (0.01), contrast (10.57), number of pixel change rate (4.86), unified average change intensity (33.66), and more are in favor of our proposed encryption scheme. To the best of our knowledge, this research is also one of the first studies that applies PPDL-based techniques to satellite image data in any capacity.

Secure Two-Party Association Rule Mining Based on One-Pass FP-Tree

2011 ◽  
Vol 5 (2) ◽  
pp. 13-32 ◽  
Author(s):  
Golam Kaosar ◽  
Xun Yi
Keyword(s):  
Association Rule ◽  
Association Rule Mining ◽  
Data Privacy ◽  
Homomorphic Encryption ◽  
Secure Computation ◽  
Rule Mining ◽  
Fully Homomorphic Encryption ◽  
Popular Method ◽  
Database Server ◽  
Tree Method

Frequent Path tree (FP-tree) is a popular method to compute association rules and is faster than Apriori-based solutions in some cases. Association rule mining using FP-tree method cannot ensure entire privacy since frequency of the itemsets are required to share among participants at the first stage. Moreover, FP-tree method requires two scans of database transactions which may not be the best solution if the database is very large or the database server does not allow multiple scans. In addition, one-pass FP-tree can accommodate continuous or periodically changing databases without restarting the process as opposed to a regular FP-tree based solution. In this paper, the authors propose a one-pass FP-tree method to perform association rule mining without compromising any data privacy among two parties. A fully homomorphic encryption system over integer numbers is applied to ensure secure computation among two data sites without disclosing any number belongs to themselves.

On Fully Homomorphic Encryption for Privacy-Preserving Deep Learning

2019 ◽  
Author(s):  
Nestor J. Hernandez Marcano ◽  
Mads Moller ◽  
Soren Hansen ◽  
Rune Hylsberg Jacobsen
Keyword(s):  
Deep Learning ◽  
Homomorphic Encryption ◽  
Privacy Preserving ◽  
Fully Homomorphic Encryption

scholarly journals Is Homomorphic Encryption-Based Deep Learning Secure Enough?

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 7806
Author(s):  
Jinmyeong Shin ◽  
Seok-Hwan Choi ◽  
Yoon-Ho Choi
Keyword(s):  
Deep Learning ◽  
Data Privacy ◽  
Homomorphic Encryption ◽  
Communication Link ◽  
Sensitive Information ◽  
Learning Technology ◽  
User Privacy ◽  
Security Vulnerabilities ◽  
Adversarial Attack ◽  
Privacy Problem

As the amount of data collected and analyzed by machine learning technology increases, data that can identify individuals is also being collected in large quantities. In particular, as deep learning technology—which requires a large amount of analysis data—is activated in various service fields, the possibility of exposing sensitive information of users increases, and the user privacy problem is growing more than ever. As a solution to this user’s data privacy problem, homomorphic encryption technology, which is an encryption technology that supports arithmetic operations using encrypted data, has been applied to various field including finance and health care in recent years. If so, is it possible to use the deep learning service while preserving the data privacy of users by using the data to which homomorphic encryption is applied? In this paper, we propose three attack methods to infringe user’s data privacy by exploiting possible security vulnerabilities in the process of using homomorphic encryption-based deep learning services for the first time. To specify and verify the feasibility of exploiting possible security vulnerabilities, we propose three attacks: (1) an adversarial attack exploiting communication link between client and trusted party; (2) a reconstruction attack using the paired input and output data; and (3) a membership inference attack by malicious insider. In addition, we describe real-world exploit scenarios for financial and medical services. From the experimental evaluation results, we show that the adversarial example and reconstruction attacks are a practical threat to homomorphic encryption-based deep learning models. The adversarial attack decreased average classification accuracy from 0.927 to 0.043, and the reconstruction attack showed average reclassification accuracy of 0.888, respectively.

A Neural Network Application of Fully Homomorphic Encryption for Cloud Computing

2020 ◽  
Author(s):  
Megha Kolhekar ◽  
Ashish Pandey ◽  
Ayushi Raina ◽  
Rijin Thomas ◽  
Vaibhav Tiwari ◽  
...  
Keyword(s):  
Neural Network ◽  
Cloud Computing ◽  
Homomorphic Encryption ◽  
Fully Homomorphic Encryption ◽  
Network Application

A Comprehensive Review on C-3 Functionalization of β-Lactams

2019 ◽  
Vol 16 (1) ◽  
pp. 3-16 ◽  
Author(s):  
Reshma Nagpal ◽  
Jitender Bhalla ◽  
Shamsher S. Bari
Keyword(s):  
Scientific Community ◽  
Organometallic Reagent ◽  
Reaction Conditions ◽  
Biological Potential ◽  
Wide Range ◽  
Economic Strategies ◽  
Synthetic Utility ◽  
Recent Advancement ◽  
Equivalent Method ◽  
Made In

Background:A lot of advancement has been made in the area of β-lactams in recent times. Most of the research is targeted towards the synthesis of novel β-lactams, their functionalization and exploring their biological potential. The C-3 functionalization of β-lactams has continued to attract considerable interest of the scientific community due to their utility as versatile intermediates in organic synthesis and their therapeutic applications. This has led to the significant increase in efforts towards developing efficient and economic strategies for C-3 functionalized β-lactams.Objective:The present review aims to highlight recent advancement made in C-3 functionalization of β-lactams.Conclusion:To summarize, functionalization of β-lactams at C-3 is an essential aspect of β-lactam chemistry in order to improve/modify its synthetic utility as well as biological potential. The C-3 carbocation equivalent method has emerged as an important and convenient strategy for C-3 functionalization of β-lactam heterocycles which provides a wide range of β-lactams viz. 3-alkylated β-lactams, 3-aryl/heteroarylated β-lactams, 3- alkoxylated β-lactams. On the other hand, base mediated functionalization of β-lactams via carbanion intermediate is another useful approach but their scope is limited by the requirement of stringent reaction conditions. In addition to this, organometallic reagent mediated α-alkylation of 3-halo/3-keto-β-lactams also emerged as interesting methods for the synthesis of functionalized β-lactams having good yields and diastereoselectivities.

Sign in / Sign up

Export Citation Format

Share Document