With the continuous maturity and development of the big data technology system, deep learning has been widely used in the field of the Industrial Internet of Things. However, the traditional training model with centralized data is prone to the leakage of private information in the industry, such as facial information. In recent years, federated learning solves the problem of privacy leakage caused by data sharing by not sharing data and only contributing to local models. Federated learning does not share data, which also makes it impossible to evaluate the contribution of each client to the federated task. We propose a federated learning framework based on data value evaluation. In this method, under the premise of effectively completing the training task of federated learning and ensuring the privacy of client data, a data value evaluator is designed in the central server, and the model uploaded by the client is evaluated to obtain the corresponding selection probability as the model aggregation weight. Experimental results show that the proposed method improves the accuracy of the global model obtained by existing federated aggregation.
With the popularity of cloud computing, cloud storage technology has also been widely used. Among them, data integrity verification is a hot research topic. At present, the realization of public auditing has become the development trend of integrity verification. Most existing public auditing schemes rarely consider some indispensable functions at the same time. Thus, in this article, we propose a comprehensive public auditing scheme (PDBPA) that can simultaneously support data privacy protection, data dynamics, and multi-user batch auditing. To guarantee privacy protection during the audit process, our PDBPA design a new method of constructing audit proof, which combines random masking techniques and bilinear properties of bilinear pairing. Not only can it ensure that TPA performs audits correctly, but it can also prevent it from exploring the user's sensitive data. In addition, by utilizing the modified dynamic hash table, which is a novel and small two-dimensional data structure, data dynamics can be effectively achieved. Furthermore, we provide a detailed process for the third-party auditors to perform batch audits for multiple users. Moreover, we give the detailed and rigorous security analysis in defending against forgery attack, replace attack, and replay attack. Performance evaluations demonstrate that our PDBPA scheme is effective and feasible. K E Y W O R D Sbatch auditing, cloud computing, data dynamics, data privacy protection, public auditing, security cloud storage INTRODUCTIONWith the advent of the information era, more and more people choose to outsource their data to cloud storage servers to save local storage space. Cloud server provider (CSP) supplies users with large-capacity, high-performance storage services, and users only need to determine service type according to own needs. However, because users have lost physical control of outsourced data, people have doubts about the security and integrity of data on the cloud. For example, untrustworthy CSP may deliberately discard data that users do not frequently access to save storage space; or lose user data due to their own mistakes but choose to conceal clients to maintain their reputation. Thus, it is a hard challenge whether the cloud storage system and its provider can meet the user's security requirements for data storage. To secure this, designing the data integrity checking scheme that can verify the integrity of outsourced data and resist malicious CSP has become a research hotspot for scholars.The traditional remote data integrity checking schemes require the user to download all the data blocks that have been uploaded to the CSP to the local, and then perform the verification, which is neither practical nor advisable. In fact, this is the method adopted by the private verification and has two gaps: (a) It will inevitably bring huge costs to the data owner (DO), especially when the DO possess the device with tight storage space
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.