Filters








17,014 Hits in 5.0 sec

Rank Consistency based Multi-View Learning

Han-Jia Ye, De-Chuan Zhan, Yuan Miao, Yuan Jiang, Zhi-Hua Zhou
2015 Proceedings of the 24th ACM International on Conference on Information and Knowledge Management - CIKM '15  
Thus, the proposed RANC framework provides a privacy-preserving way for multi-view learning.  ...  In this paper, we propose a novel multi-view learning framework which works in a hybrid fusion manner.  ...  The main contributions of this paper can be summarized as follows: • A novel rank consistency criterion based multi-view learning framework (RANC), which preserves data privacy of multiple channels, i.e  ... 
doi:10.1145/2806416.2806552 dblp:conf/cikm/YeZMJZ15 fatcat:oxnknsrhejgcjkysngwoe64be4

A Critical Overview of Privacy-Preserving Approaches for Collaborative Forecasting [article]

Carla Gonçalves and Ricardo J. Bessa and Pierre Pinson
2020 arXiv   pre-print
The analysis shows that state-of-the-art techniques have limitations in preserving data privacy, such as a trade-off between privacy and forecasting accuracy, while the original data in iterative model  ...  The paper also provides mathematical proofs and numerical analysis to evaluate existing privacy-preserving methods, dividing them into three groups: data transformation, secure multi-party computations  ...  Table 1 : 1 Summary of state-of-the-art privacy-preserving approaches.  ... 
arXiv:2004.09612v6 fatcat:qbomrvhhkberzopkvyllz75pxe

Slicing: A New Approach to Privacy Preserving Data Publishing [article]

Tiancheng Li, Ninghui Li, Jian Zhang, Ian Molloy
2009 arXiv   pre-print
Several anonymization techniques, such as generalization and bucketization, have been designed for privacy preserving microdata publishing.  ...  In this paper, we present a novel technique called slicing, which partitions the data both horizontally and vertically.  ...  DISCUSSIONS AND FUTURE WORK This paper presents a new approach called slicing to privacy-preserving microdata publishing.  ... 
arXiv:0909.2290v1 fatcat:zhq2ig4w65etdehp72ezg5mfm4

Slicing: A New Approach for Privacy Preserving Data Publishing

Tiancheng Li, Ninghui Li, Jian Zhang, Ian Molloy
2012 IEEE Transactions on Knowledge and Data Engineering  
Several anonymization techniques, such as generalization and bucketization, have been designed for privacy preserving microdata publishing.  ...  In this paper, we present a novel technique called slicing, which partitions the data both horizontally and vertically.  ...  DISCUSSIONS AND FUTURE WORK This paper presents a new approach called slicing to privacy-preserving microdata publishing.  ... 
doi:10.1109/tkde.2010.236 fatcat:smn5wqrorjd5fnrpk3mnh5t6m4

Privacy-preserving data mining: A feature set partitioning approach

Nissim Matatov, Lior Rokach, Oded Maimon
2010 Information Sciences  
In privacy-preserving data mining (PPDM), a widely used method for achieving data mining goals while preserving privacy is based on k-anonymity.  ...  The most common approach for achieving compliance with k-anonymity is to replace certain values with less specific but semantically consistent values.  ...  He has been a most helpful assistant in proofreading and improving the manuscript.  ... 
doi:10.1016/j.ins.2010.03.011 fatcat:lkyq2ufvbvbaxmqwjn7w63dl2a

A privacy-preserving exception handling approach for dynamic mobile crowdsourcing applications

Yanwei Xu, Hanwen Liu, Chao Yan
2019 EURASIP Journal on Wireless Communications and Networking  
In view of this challenge, in this paper, a novel privacy-preserving exception handling approach, named ExH Simhash , is put forward based on Simhash technique.  ...  However, for a mobile crowdsourcing task being executed by a set of workers, a pre-selected worker may become unavailable due to various exceptions.  ...  In view of this challenge, a novel privacy-preserving exception handling approach, named ExH Simhash , is put forward in this paper. terms of substitution equivalence and computational time.  ... 
doi:10.1186/s13638-019-1439-8 fatcat:wxofcctdj5gsvduczxzav3rqui

Beyond federated learning: On confidentiality-critical machine learning applications in industry

Werner Zellinger, Volkmar Wieser, Mohit Kumar, David Brunner, Natalia Shepeleva, Rafa Gálvez, Josef Langer, Lukas Fischer, Bernhard Moser
2021 Procedia Computer Science  
Second, we envision a new confidentialitypreserving approach for smart manufacturing applications based on the more general setting of transfer learning, and envision its implementation in a module-based  ...  Second, we envision a new confidentialitypreserving approach for smart manufacturing applications based on the more general setting of transfer learning, and envision its implementation in a module-based  ...  Our recent work [23] has suggested a novel entropy based approach for resolving the privacy-utility trade-off for real-valued data matrices.  ... 
doi:10.1016/j.procs.2021.01.296 fatcat:ov3banqt4rhfbbx6hzdh3od3hu

Deep Learning Towards Mobile Applications [article]

Ji Wang and Bokai Cao and Philip S. Yu and Lichao Sun and Weidong Bao and Xiaomin Zhu
2018 arXiv   pre-print
Inspired by the tremendous success achieved by deep learning in many machine learning tasks, it becomes a natural trend to push deep learning towards mobile applications.  ...  networks, the privacy and security concerns about individuals' data, and so on.  ...  The property of differential privacy theory makes it a foundation to design privacy-preserving training approaches. Shokri et al.  ... 
arXiv:1809.03559v1 fatcat:e4kwy7tb2bgqdizijjvkqyurfy

A compressive multi-kernel method for privacy-preserving machine learning [article]

Thee Chanyaswad, J. Morris Chang, S.Y. Kung
2021 arXiv   pre-print
Compressive Privacy is a privacy framework that employs utility-preserving lossy-encoding scheme to protect the privacy of the data, while multi-kernel method is a kernel based machine learning regime  ...  These results indicate a promising direction for research in privacy-preserving machine learning.  ...  The compressive multi-kernel learning method, therefore, presents a promising framework for privacy-preserving machine learning applications. II. PRIOR WORKS A.  ... 
arXiv:2106.10671v1 fatcat:lhvq7yz6jvdk3dnaked46uvur4

A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics [article]

Seyed Ali Osia, Ali Shahin Shamsabadi, Sina Sajadmanesh, Ali Taheri, Kleomenis Katevas, Hamid R. Rabiee, Nicholas D. Lane, Hamed Haddadi
2019 arXiv   pre-print
In this paper, we present a hybrid approach for breaking down large, complex deep neural networks for cooperative, privacy-preserving analytics.  ...  We evaluate the privacy benefits of this approach based on the information exposed to the cloud service. We also assess the local inference cost of different layers on a modern handset.  ...  Learning with privacy Prior works have approached the problem of privacy in machine learning from a different point of view.  ... 
arXiv:1703.02952v7 fatcat:due6wly2x5acnavtq22eqwfi6a

Swarm Learning for decentralized and confidential clinical machine learning

Stefanie Warnat-Herresthal, COVID-19 Aachen Study (COVAS), Hartmut Schultze, Krishnaprasad Lingadahalli Shastry, Sathyanarayanan Manamohan, Saikat Mukherjee, Vishesh Garg, Ravi Sarveswara, Kristian Händler, Peter Pickkers, N. Ahmad Aziz, Sofia Ktena (+55 others)
2021 Nature  
Here, to facilitate the integration of any medical data from any data owner worldwide without violating privacy laws, we introduce Swarm Learninga decentralized machine-learning approach that unites edge  ...  computing, blockchain-based peer-to-peer networking and coordination while maintaining confidentiality without the need for a central coordinator, thereby going beyond federated learning.  ...  SL provides confidentiality-preserving machine learning by design and can inherit new developments in differential privacy algorithms 40 , functional encryption 41 , or encrypted transfer learning approaches  ... 
doi:10.1038/s41586-021-03583-3 pmid:34040261 fatcat:5ule2vsgbngltmi6b7ubr24yga

Federated Deep Learning with Bayesian Privacy [article]

Hanlin Gu, Lixin Fan, Bowen Li, Yan Kang, Yuan Yao, Qiang Yang
2021 arXiv   pre-print
Deep learning with Differential Privacy (DP) was implemented as a practical learning algorithm at a manageable cost in complexity.  ...  As a concrete use case, we demonstrate that a novel federated deep learning method using private passport layers is able to simultaneously achieve high model performance, privacy-preserving capability  ...  Bayesian Privacy in Federated learning In this work we consider a federated deep learning scenario, where K participants collaboratively learn a multi-layered deep neural network model without exposing  ... 
arXiv:2109.13012v1 fatcat:qx5ip7kdkneu5ew3v7zhz5x24i

Privacy Disclosure and Preservation in Learning with Multi-Relational Databases

Hongyu Guo, Herna L. Viktor, Eric Paquet
2011 Journal of Computing Science and Engineering  
This paper demonstrates this potential for privacy leakage in multi-relational classification and illustrates how such potential leaks may be detected.  ...  We propose a method to generate a ranked list of subschemas that maintains the predictive performance on the class attribute, while limiting the disclosure risk, and predictive accuracy, of confidential  ...  ACKNOWLEDGMENTS This paper extends our earlier work, as reported in the 2nd IEEE International Workshop on Privacy Aspects of Data Mining (PADM2010) (Guo et al. [42] ).  ... 
doi:10.5626/jcse.2011.5.3.183 fatcat:k5q2rpcvbred5nyxkdvqe6ugbq

Machine Learning-Based Semantic Entity Alignment for Multi-Source Data: a Systematic Literature Review

Alex Boyko, Siamak Farshidi, Zhiming Zhao
2021 Zenodo  
Many machine learning-based semantic entity alignment approaches have been proposed by the recent studies in the field.  ...  ML-based semantic entity alignment approaches.  ...  Pandl et al. [51] Data Privacy Preservation The privacy-preserving aspects and techniques of machine learning cover the family of methods and architectures developed to protect the privacy of people whose  ... 
doi:10.5281/zenodo.6328248 fatcat:kl4julgduffzzhyxztsfxzsw3a

Fairness-Driven Private Collaborative Machine Learning [article]

Dana Pessach, Tamir Tassa, Erez Shmueli
2021 arXiv   pre-print
In this work we suggest a feasible privacy-preserving pre-process mechanism for enhancing fairness of collaborative machine learning algorithms.  ...  However, such data sharing introduces significant privacy challenges.  ...  The second approach is based on Secure Multi-party Computation (SMC) (Lindell and Pinkas 2000) .  ... 
arXiv:2109.14376v1 fatcat:5zpljrjawjgthee7imyo2mltoy
« Previous Showing results 1 — 15 out of 17,014 results