A privacy-preserving decentralized credit scoring method based on multi-party information

2023 | Decision Support Systems | Citations: 0

Authors: He, Haoran; Wang, Zhao; Jain, Hemant; Jiang, Cuiqing; Yang, Shanlin

Abstract: With society's wide-scale adoption of information technology, significant inform ... Expand

Abstract: With society's wide-scale adoption of information technology, significant information about borrowers is distributed across various parties, information that can be jointly used to improve credit scoring. However, use of such information faces many challenges, such as the problems of preserving privacy and information redun­ dancy. To address these challenges in leveraging multi-source information for credit scoring, we propose a decentralized multi-party method based on logistic regression. Specifically, we formulate a logistic regression model using the vertical federated learning paradigm. To preserve data privacy during multi-party collaborative model training, we use additively homomorphic encryption based on the second-order Taylor series expansion of the loss function and its gradient. To address information redundancy and to improve the performance of the credit scoring model, we use the proposed HE-DPGD algorithm to estimate the distributed coefficients in a privacy-preserving setting. Empirical evaluation shows that the proposed method can leverage information from multiple parties securely and effectively. Collapse

Topics: privacy homomorphic encryption logistics management online lending missing data

Methods: computational algorithm machine learning federated learning logistic regression experiment

Business model implications of privacy-preserving technologies in data marketplaces: The case of multi-party computation

2021 | European Conference On Information Systems | Citations: 0

Authors: Agahari, Wirawan; Dolci, Riccardo; Reuver, Mark de

Abstract: Privacy-preserving technologies could allow data marketplaces to deliver techni ... Expand

Abstract: Privacy-preserving technologies could allow data marketplaces to deliver technical assurances to companies on data privacy and control. However, how such technologies change the business model of data marketplaces is not fully understood. This paper aims to bridge this gap by focusing on multiparty computation (MPC) as a cryptographic technology that is currently being hyped. Based on interviews with privacy and security experts, we find that MPC enables data marketplaces to employ a "privacy-as-a-service" business model, which goes beyond privacy-preserving data exchange. Depending on the architecture, MPC could transform data marketplaces into data brokers or data aggregators. More complex architectures might lead to more robust security guarantees and lower trust requirements towards data marketplace operators. Furthermore, MPC enables new offerings of privacy-preserving analytics and services as new revenue sources. Our findings contribute to developing business models of privacy-preserving data marketplaces to unlock the potential of data sharing in a digitized economy. Collapse

Topics: privacy business model value creation peer-to-peer model digital platform

Methods: qualitative interview qualitative coding design artifact archival research experiment

Anonymous Blockchain-based System for Consortium

2021 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Wang, Qin; Chen, Shiping; Xiang, Yang

Abstract: Blockchain records transactions with various protection techniques against tampe ... Expand

Abstract: Blockchain records transactions with various protection techniques against tampering. To meet the requirements on cooperation and anonymity of companies and organizations, researchers have developed a few solutions. Ring signature-based schemes allow multiple participants cooperatively to manage while preserving their individuals’ privacy. However, the solutions cannot work properly due to the increased computing complexity along with the expanded group size. In this article, we propose a Multi-center Anonymous Blockchain-based (MAB) system, with joint management for the consortium and privacy protection for the participants. To achieve that, we formalize the syntax used by the MAB system and present a general construction based on a modular design. By applying cryptographic primitives to each module, we instantiate our scheme with anonymity and decentralization. Furthermore, we carry out a comprehensive formal analysis of our exemplified scheme. A proof of concept simulation is provided to show the feasibility. The results demonstrate security and efficiency from both theoretical perspectives and practical perspectives. Collapse

Topics: anonymity data encryption public key encryption blockchain privacy

Methods: computational algorithm experiment design artifact literature study simulation

PANDA: Partitioned Data Security on Outsourced Sensitive and Non-sensitive Data

2020 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Mehrotra, Sharad; Sharma, Shantanu; Ullman, Jeffrey D.; Ghosh, Dhrubajyoti; Gupta, Peeyush; Mishra, Anurag

Abstract: Despite extensive research on cryptography, secure and efficient query processin ... Expand

Abstract: Despite extensive research on cryptography, secure and efficient query processing over outsourced data remains an open challenge. This article continues along with the emerging trend in secure data processing that recognizes that the entire dataset may not be sensitive and, hence, non-sensitivity of data can be exploited to overcome limitations of existing encryption-based approaches. We first provide a new security definition, entitled partitioned data security, for guaranteeing that the joint processing of non-sensitive data (in cleartext) and sensitive data (in encrypted form) does not lead to any leakage. Then, this article proposes a new secure approach, entitled query binning (QB), that allows secure execution of queries over non-sensitive and sensitive parts of the data. QB maps a query to a set of queries over the sensitive and non-sensitive data in a way that no leakage will occur due to the joint processing over sensitive and non-sensitive data. In particular, we propose secure algorithms for selection, range, and join queries to be executed over encrypted sensitive and cleartext non-sensitive datasets. Interestingly, in addition to improving performance, we show that QB actually strengthens the security of the underlying cryptographic technique by preventing size, frequency-count, and workload-skew attacks. Collapse

Topics: data security data encryption cloud computing data breach outsourcing

Methods: computational algorithm design artifact experiment

A Novel Group Ownership Delegate Protocol for RFID Systems

2019 | Information Systems Frontiers | Citations: 9

Authors: Lee, Cheng-Chi; Li, Chun-Ta; Cheng, Chung-Lun; Lai, Yan-Ming; Vasilakos, Athanasios V.

Abstract: In recent years, Radio Frequency Identification (RFID) applications of various k ... Expand

Abstract: In recent years, Radio Frequency Identification (RFID) applications of various kinds have been blooming. However, along with the stunning advancement have come all sorts of security and privacy issues, for RFID tags oftentimes store private data and so the permission to read a tag or any other kind of access needs to be carefully controlled. Therefore, of all the RFID-related researches released so far, a big portion focuses on the issue of authentication. There have been so many cases where the legal access to or control over a tag needs to be switched from one reader to another, which has encouraged the development of quite a number of different kinds of ownership transfer protocols. On the other hand, not only has the need for ownership transfer been increasing, but a part of it has also been evolving from individual ownership transfer into group ownership transfer. However, in spite of the growing need for practical group ownership transfer services, little research has been done to offer an answer to the need. In this paper, we shall present a new RFID time-bound group ownership delegate protocol based on homomorphic encryption and quadratic residues. In addition, in order to provide more comprehensive service, on top of mutual authentication and ownership delegation, we also offer options for the e-th time verification as well as the revocation of earlier delegation. Collapse

Topics: electronic authentication radio frequency identification homomorphic encryption authorization privacy

Methods: literature study

Privacy-preserving Distributed Analytics: Addressing the Privacy-Utility Tradeoff Using Homomorphic Encryption for Peer-to-Peer Analytics

2015 | International Conference on Information Systems | Citations: 0

Authors: Bhattacharya, Prasanta; Phan, Tuan; Liu, Linlin

Abstract: Data is becoming increasingly valuable, but concerns over its security and priva ... Expand

Abstract: Data is becoming increasingly valuable, but concerns over its security and privacy have limited its utility in analytics. Researchers and practitioners are constantly facing a privacy-utility tradeoff where addressing the former is often at the cost of the data utility and accuracy. In this paper, we draw upon mathematical properties of partially homomorphic encryption, a form of asymmetric key encryption scheme, to transform raw data from multiple sources into secure, yet structure-preserving encrypted data for use in statistical models, without loss of accuracy. We contribute to the literature by: i) proposing a method for secure and privacy-preserving analytics and illustrating its utility by implementing a secure and privacy-preserving version of Maximum Likelihood Estimator, “s-MLE”, and ii) developing a web-based framework for privacy-preserving peer-to-peer analytics with distributed datasets. Our study has widespread applications in sundry industries including healthcare, finance, ecommerce etc., and has multi-faceted implications for academics, businesses, and governments. Collapse

Topics: data encryption privacy public key encryption peer-to-peer model homomorphic encryption

Methods: logistic regression simulation design artifact conceptual modelling design science

Confidential Information-Sharing for Automated Sustainability Benchmarks

2011 | International Conference on Information Systems | Citations: 0

Authors: Kerschbaum, Florian; StrÃ, Jens

Abstract: The pressure on enterprises to manage and improve their environmental sustainabi ... Expand

Abstract: The pressure on enterprises to manage and improve their environmental sustainability is steadily increasing. Despite the growing awareness in the IS community and business practice, current IS solutions remain in an initial state. Sustainability benchmarking is seen as a novel and effective tool in this context. However, sustainability benchmarking faces two major obstacles: First, the heterogeneity of the data requires significant pre-processing, and, second, the sensitivity of the data causes enterprises to reluctantly share this data. Our contribution is twofold: After analyzing the data input problem and identifying appropriate and available solutions, we present a secure sustainability benchmarking service (SBS) to overcome the information-sharing problem. Our service uses homomorphic encryption to protect the data during processing and differential privacy to protect against leakages from the reports. Finally, we evaluate in detail a prototypical implementation of this secure sustainability benchmarking service and illustrate its applicability in industry. Collapse

Topics: data encryption supply chain management enterprise resource planning homomorphic encryption public key encryption

Methods: design artifact experiment company material computational algorithm data envelopment analysis

Secure and Sustainable Benchmarking in Clouds: A Multi-Party Cloud Application with an Untrusted Service Provider

2011 | Business & Information Systems Engineering | Citations: 0

Authors: Kerschbaum, Florian

Abstract: Cloud computing entails a novel security threat: The cloud service provider is ... Expand

Abstract: Cloud computing entails a novel security threat: The cloud service provider is entrusted with the data of all its customers. Encryption may provide the solution. Using the example of collaborative benchmarking the authors present and evaluate the exemplary design and implementation that operates on encrypted data. Collapse

Topics: cloud computing homomorphic encryption Java data encryption web service

Methods: experiment cluster analysis computational algorithm time series analysis longitudinal research

Voting Early and Often Can Be a Good Thing

2007 | Americas Conference on Information Systems | Citations: 0

Authors: Post, Gerald

Abstract: The current political climate has almost ruled out the use of Internet voting. M ... Expand

Abstract: The current political climate has almost ruled out the use of Internet voting. Many politicians, led by vocal computer scientists, are pushing for voter verified paper receipts; which is likely to push us even further away from even electronic voting systems. On the other hand, cryptographers have created homomorphic encryption and non-interactive zero-knowledge proofs with features that can support Internet voting. Adding a few more protocols, including an extended voting period and repeat voting can solve the remaining problems need to make Internet voting at least as secure as existing systems. Collapse

Topics: spyware homomorphic encryption