CN115499186A - Privacy protection scheme based on secure multi-party calculation truth value discovery in mobile crowd sensing - Google Patents
Privacy protection scheme based on secure multi-party calculation truth value discovery in mobile crowd sensing Download PDFInfo
- Publication number
- CN115499186A CN115499186A CN202211109100.9A CN202211109100A CN115499186A CN 115499186 A CN115499186 A CN 115499186A CN 202211109100 A CN202211109100 A CN 202211109100A CN 115499186 A CN115499186 A CN 115499186A
- Authority
- CN
- China
- Prior art keywords
- perception
- data
- sensing
- server
- privacy protection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 13
- 238000005516 engineering process Methods 0.000 claims abstract description 8
- 230000008447 perception Effects 0.000 claims description 76
- 239000000654 additive Substances 0.000 claims description 10
- 230000000996 additive effect Effects 0.000 claims description 10
- 230000001953 sensory effect Effects 0.000 claims description 9
- 238000012358 sourcing Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/20—Network architectures or network communication protocols for network security for managing network security; network security policies in general
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/08—Key distribution or management, e.g. generation, sharing or updating, of cryptographic keys or passwords
- H04L9/0816—Key establishment, i.e. cryptographic processes or cryptographic protocols whereby a shared secret becomes available to two or more parties, for subsequent use
- H04L9/085—Secret sharing or secret splitting, e.g. threshold schemes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L2209/00—Additional information or applications relating to cryptographic mechanisms or cryptographic arrangements for secret or secure communication H04L9/00
- H04L2209/46—Secure multiparty computation, e.g. millionaire problem
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of Internet of things, and discloses a privacy finding method based on safe multi-party calculation truth in mobile crowd sensing, which relates to a privacy protection scheme. The privacy protection scheme is discovered based on the secure multi-party computing truth value in the mobile crowd sensing, a secret sharing technology and secure multi-party computing are adopted, a user only needs to upload data to a server, the server calculates the data truth value and the user weight by executing a secure multi-party computing protocol, interaction between the user and the server is reduced, and a cryptographic algorithm with high computing cost is not adopted, so that the scheme has high execution efficiency.
Description
Technical Field
The invention relates to the technical field of Internet of things, in particular to a privacy protection scheme based on safe multi-party calculation truth value discovery in mobile crowd sensing.
Background
With the continuous development and accelerated integration of the internet of things, big data and artificial intelligence technologies, mobile Crowd Sensing (MCS) is a new data sensing mode and becomes a research hotspot at the international leading edge in recent years. Unlike the traditional internet of things mode of fixedly deploying a sensor network, the MCS takes a large number of mobile intelligent terminals of common users as basic sensing units, performs data sensing on the physical world, acquires various information such as personal behaviors, equipment states and surrounding environments, and solves the problems of high system cost, difficult maintenance, limited scale, inflexible performance and the like in the traditional data collection mode. Today's portable intelligent terminal devices integrate a large number of sensor elements and have very strong computing performance, can meet the requirements of more and more sensing tasks on the device performance and have very low sensing cost. The low-cost and efficient data collection mode enables the MCS to be widely applied, such as health data collection, traffic condition analysis, environmental noise monitoring and the like, greatly enriches various applications and services of a novel smart city, and promotes realization of 'everything interconnection and smart intercommunication'. In mobile crowd-sourcing perception, mobile users are participants, both collectors and producers of data and users and beneficiaries. Various resources (such as power, flow, road charge and the like, and the consumed resources are collectively called as sensing cost) are inevitably consumed during the participation of the user in the sensing task, so that a reasonable incentive mechanism needs to be designed to ensure the enthusiasm of the user for participation. For example, in a monetary reward-based incentive mechanism, the sensory platform may offer additional monetary rewards to the user upon payment of the user's perceived cost, in order to incentivize continued participation by the user.
Some schemes require frequent user participation in the execution process, however, most users can hardly guarantee that the schemes are on line for a long time, which causes uncertainty in scheme execution, and although some researches solve the problem of interaction between users and servers to some extent, users only need to upload perception data and do not need to participate in any calculation, these schemes still inevitably use computationally expensive cryptography primitives to guarantee privacy security, which causes the calculation efficiency to decrease rapidly with the increase of perception users.
Disclosure of Invention
The invention aims to provide a privacy protection scheme based on safe multi-party calculation truth value discovery in mobile crowd sensing so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: a privacy protection scheme is discovered based on a safe multi-party calculation truth value in mobile crowd sensing, and the privacy protection scheme comprises the following steps:
s1: the data requester specifies a desired perception task (e.g., ambient noise monitoring, indoor map information collection, and road congestion condition monitoring at a specified location, etc.) and requests a perception service from the perception platform.
S2: the sensory platform recruits sensory users.
S3: and the perception user collects perception data according to the use of the intelligent terminal equipment.
S4: the perception user uploads perception data to the perception platform, and in order to protect privacy, the perception user distributes the perception data to three servers of the perception platform by adopting a secret sharing technology.
S5:
The three servers in the perception platform adopt a secure multiparty arithmetic calculation protocol to execute the calculation of truth value discovery, and the calculated truth value is still the secret sharing share of the servers.
S6: the data requester can restore the true value after summarizing the true shared shares of the three servers.
Preferably, the collected perception data x is divided by the perception userRespectively sent to three servers S 1 ,S 2 ,S 3 Storing and usingPresentation to a server S i Server S, share of 1 ,S 2 ,S 3 The privacy-preserving true-value discovery computation is performed jointly using a shared secure multi-party computation scheme.
Preferably, the shared secure multiparty computation scheme may implement basic computations, referred to herein as basic computation protocols, such as secure addition, multiplication, etc., e.g., given share of input data sharesAndserver S i Can be calculated by performingAndthe addition and multiplication operations on the shared shares are realized without revealing any private information about the inputs and the computation output.
Preferably, the shared is based on additive secret sharing, so that addition and subtraction operations on shared shares are performedAnd operation of multiplying a shared share by a constantAll can be directly realized according to the property of additive secret sharing, and the multiplication operation among shared shares needs to be constructed by using a Du-Atallah multiplication protocol.
Preferably, after the sensing user receives the sensing task, the S4 collects the sensing data by using the intelligent terminal device, and the sensing data is uploaded to the server by an additive secret sharing method.
Preferably, the perception platform recruits K perception users { u } 1 ,u 2 ,…,u K Help data requesters to collect M perceptual tasks T 1 ,T 2 ,…,T M The perception data of users u i All sensory data collected is noted as { x } i1 ,x i2 ,…,x iM In which x ij Representing user u i For task T j The perception data collected.
Preferably, the server S 1 ,S 2 ,S 3 Respectively hold calculated true shareEach server sends the true share held by each server to the data requester, and the data requester restores the true share according to the following formula
Preferably, the sensing task number M and the sensing user number K are public, and any one of the systems can be acquired at any time.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the privacy protection scheme discovered based on the secure multi-party computing truth value in the mobile crowd sensing, due to the fact that a secret sharing technology and secure multi-party computing are adopted, a user only needs to upload data to a server, the server calculates the data truth value and the user weight through executing a secure multi-party computing protocol, interaction between the user and the server is greatly reduced, and meanwhile, due to the fact that a cryptographic algorithm with high computing overhead is not adopted, the scheme has high execution efficiency.
2. In the mobile crowd sensing, a privacy protection scheme is discovered based on a safe multi-party computing true value, sensing data is split by adopting a secret sharing technology, and the true value is computed by adopting the safe multi-party computing among a plurality of servers at the cloud.
3. In the mobile crowd sensing, a privacy protection scheme is discovered based on a safe multiparty calculation truth value, a user incentive mechanism driven by data quality is designed by utilizing user weight obtained by truth value discovery calculation, and the protection of user privacy is realized.
Drawings
FIG. 1 is a diagram of a perceptual task system framework;
FIG. 2 is a diagram of a sensory platform system framework.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the present invention provides the following technical solutions:
a privacy protection scheme is discovered based on a safe multi-party calculation truth value in mobile crowd sensing, and the privacy protection scheme comprises the following steps:
s1: a data requester specifies required sensing tasks (such as environmental noise monitoring at a specified position, indoor map information collection, road congestion condition monitoring and the like) and requests sensing services from a sensing platform, the number M of the sensing tasks and the number K of sensing users are public, and any one of the sensing tasks and the sensing users can be acquired at any time in the system.
S2: the sensory platform recruits sensory users.
S3: the perception user divides the perception data into perception data x according to the perception data x collected by using the intelligent terminal equipmentRespectively sent to three servers S 1 ,S 2 ,S 3 Storing and usingPresentation to the Server S i Share of, server S 1 ,S 2 ,S 3 The privacy-preserving true-value discovery computation is performed jointly using a shared secure multi-party computation scheme.
The shared secure multiparty computation scheme may implement basic computations, referred to herein as basic computation protocols, such as secure addition, multiplication, etc., e.g., given share of input data sharesAndserver S i Can be calculated by performingAnd implementing addition and multiplication operations on shared shares without revealing any private information about inputs and computation outputs, shared being based on additive secret sharing, whereby addition and subtraction operations on shared shares are performedAnd operation of multiplying a shared share by a constantAll the methods can be directly realized according to the property of additive secret sharing, and for the multiplication operation among shared shares, the multiplication operation needs to be constructed by using a Du-Atallah multiplication protocol, and the shared multiplication protocol is shown by an algorithm 2:
s4: the perception user uploads perception data to the perception platform, the perception user collects the perception data by using intelligent terminal equipment after receiving a perception task, the perception data are uploaded to the server through an additive secret sharing method, and in order to protect privacy, the perception user distributes the perception data to the three servers of the perception platform by adopting a secret sharing technology.
The perception platform recruits K perception users (u) 1 ,u 2 ,…,u K Help data requesters to collect M perceptual tasks T 1 ,T 2 ,…,T M The perception data of users u i All sensory data collected is noted as { x } i1 ,x i2 ,…,x iM In which x is ij Representing user u i For task T j Collected perception data, server S 1 ,S 2 ,S 3 Respectively hold calculated true shareEach server sends the true share held by each server to the data requester, and the data requester restores the true share according to the following formula
S5: the three servers in the perception platform adopt a secure multiparty arithmetic calculation protocol to execute the calculation of truth value discovery, and the calculated truth value is still the secret sharing share of the servers.
S6: the data requester can restore the true value after summarizing the true value sharing shares of the three servers, the perception user collects perception data by using intelligent terminal equipment after receiving the perception task, and the perception data are uploaded to the servers through an additive secret sharing method.
The perception platform recruits K perception users (u) 1 ,u 2 ,…,u K Help data requesters to collect M perceptual tasks T 1 ,T 2 ,…,T M The perception data of users u i All the perception data collectedIs denoted as { x i1 ,x i2 ,…,x iM In which x ij Representing user u i For task T j The perception data collected.
Finally, each perception user sends the calculated three sharing shares to the server S, the server S and the server S for storage.
The result obtained after the calculation of each server is the secret sharing share corresponding to the true value, according to the security of secret sharing, a single server cannot obtain the true result discovered by the true value, so that the security of privacy is ensured, after the calculation of the servers is finished, the respective true value sharing shares are sent to the data requester, the requester aggregates the received sharing shares to obtain the final true value result, the operations related to the true value discovery algorithm include addition, subtraction, multiplication, division and logarithm operation, the operation can be constructed by using a shared basic calculation protocol, the logarithm operation log (-) related in the weight updating step can be converted into ln (-) by adopting a bottom-changing formula, and then the approximation operation is carried out by using a Taylor series, and based on the given value, the logarithm log (x) can be represented as follows:
whereinThe logarithm algorithm is constructed according to the above formula as shown in algorithm 2:
both processes of true value discovery are essentially arithmetic operations, and the involved operations only include addition (subtraction), multiplication (division) and logarithm calculation, so that a secure multi-party arithmetic computation (secure-fractional arithmetic computing) protocol is adopted to realize true value computation, shared is a secure multi-party computing platform and provides secure multi-party arithmetic computation (such as addition, subtraction, multiplication and division and other basic operations) protocols, and all basic protocols are universal and combinable, even if a complex protocol constructed by basic operation protocols can still ensure privacy security, in the research, the true value discovery of privacy protection is realized based on the shared basic protocol, and the true value discovery of privacy protection based on the shared structure comprises the following steps:
server S i After receiving the true value data uploaded by the user, the slave computerIn the method, M random numbers (r) are randomly selected 1 ,r 2 ,…,r M ) As an initial truth share, i.e.
After the initial value setting is completed, the weight updating and the truth value updating are calculated in an iterative mode among the servers, and the calculation process is as follows:
updating the security weight: for the perception numberAccording toTrue value discovery is performed among three servers by executing Sharmind secure multiparty computing protocol, where the server (k =1,2,3) calculates the share corresponding to the weight by executing the following formula
Updating a safety truth value: after the weight update calculation is completed, the three servers perform the calculation of the true value using the user weights calculated during the weight update process, wherein the server (k =1,2,3) calculates the corresponding share of the true value by performing the following equation
After performing the weight update and the truth update of multiple iterations, the server S 1 ,S 2 ,S 3 The execution formula calculates the user weight deviation (i.e. the difference between the user weight and the average weight)And sending to a perception platform for summarizing:
aware platform executionThe user weight deviation is restored and the calculation of the distribution to each user is performed (12)User's award amount Pay i And the Budget paid by the data requester is the sensing Budget, and the K is a scaling coefficient for controlling the reward distribution:
the perception platform deploys three semi-trusted servers S 1 ,S 2 ,S 3 Compared with a double-server architecture, the three-server architecture adopted by the method can have higher tolerance on collusion behaviors, privacy can still be guaranteed not to be revealed even if collusion behaviors appear in any two servers, although more servers are deployed, higher collusion tolerance can be obtained, collusion attack is difficult to achieve, and in consideration of cost, efficiency and other factors, 3-5 servers are deployed to be a practical scheme.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in the embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A privacy protection scheme is discovered based on a safe multi-party calculation truth value in mobile crowd sensing, and is characterized by comprising the following steps:
s1: a data requester specifies a required sensing task and requests a sensing service from a sensing platform;
s2: the perception platform recruits perception users;
s3: the perception user collects perception data according to the use of the intelligent terminal equipment;
s4: the perception user uploads perception data to the perception platform, and in order to protect privacy, the perception user distributes the perception data to three servers of the perception platform by adopting a secret sharing technology;
s5: the method comprises the following steps that three servers in a perception platform adopt a secure multiparty arithmetic calculation protocol to execute calculation of truth value discovery, and the calculated truth value is still a secret sharing share of the servers;
s6: the data requester can restore the true value after summarizing the true shared shares of the three servers.
2. The privacy protection scheme for secure multi-party computing based true value discovery in mobile crowd-sourcing awareness in accordance with claim 1, wherein: the perception data x collected by S3 is divided into the perception data x by perception usersRespectively sent to three servers S 1 ,S 2 ,S 3 Storing and usingPresentation to the Server S i Server S, share of 1 ,S 2 ,S 3 The privacy-preserving true-value discovery computation is performed jointly using a shared secure multi-party computation scheme.
3. The privacy protection scheme for secure multi-party computing based true value discovery in mobile crowd sensing according to claim 2, wherein: the shared secure multiparty computation scheme may implement basic computations, referred to herein as basic computation protocols, such as secure addition, multiplication, etc., e.g., given share of input data sharesAndserver S i Can be calculated by performing Andthe addition and multiplication operations on the shared shares are realized without revealing any private information about the inputs and the computation output.
4. The privacy protection scheme for secure multi-party computing based true value discovery in mobile crowd-sourcing awareness in accordance with claim 3, wherein: the shared is based on additive secret sharing, so that addition and subtraction operations on shared shares are performedAnd operation of multiplying a shared share by a constantAll can be directly realized according to the property of additive secret sharing, and the multiplication operation among shared shares needs to be constructed by using a Du-Atallah multiplication protocol.
5. The privacy protection scheme for secure multi-party computing based true value discovery in mobile crowd-sourcing awareness in accordance with claim 1, wherein: and S4, after receiving the perception task, the perception user collects perception data by using the intelligent terminal equipment, and the perception data is uploaded to the server by an additive secret sharing method.
6. The privacy protection scheme for secure multi-party computing based true value discovery in mobile crowd-sourcing awareness in accordance with claim 5, wherein: the perception platform recruits K perception users { u 1 ,u 2 ,…,u K Help data requesters to collect M perceptual tasks T 1 ,T 2 ,…,T M The perception data of users u i All sensory data collected is noted as { x } i1 ,x i2 ,…,x iM In which x ij Representing user u i For task T j The perception data collected.
7. The privacy protection scheme for mobile crowd sensing based on secure multi-party computation truth discovery according to claim 1, wherein: the server S 1 ,S 2 ,S 3 Respectively hold calculated true shareEach server sends the true share held by each server to the data requester, and the data requester restores the true share according to the following formula
8. The privacy protection scheme for secure multi-party computing based true value discovery in mobile crowd-sourcing awareness in accordance with claim 1, wherein: s1, the number M of sensing tasks and the number K of sensing users are public, and any party in the system can obtain the sensing tasks at any time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211109100.9A CN115499186A (en) | 2022-09-13 | 2022-09-13 | Privacy protection scheme based on secure multi-party calculation truth value discovery in mobile crowd sensing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211109100.9A CN115499186A (en) | 2022-09-13 | 2022-09-13 | Privacy protection scheme based on secure multi-party calculation truth value discovery in mobile crowd sensing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115499186A true CN115499186A (en) | 2022-12-20 |
Family
ID=84469285
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211109100.9A Pending CN115499186A (en) | 2022-09-13 | 2022-09-13 | Privacy protection scheme based on secure multi-party calculation truth value discovery in mobile crowd sensing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115499186A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108494760A (en) * | 2018-03-14 | 2018-09-04 | 安徽大学 | A kind of intelligent perception true value discovery method of protection privacy |
US20200304293A1 (en) * | 2017-08-30 | 2020-09-24 | Inpher, Inc. | High-Precision Privacy-Preserving Real-Valued Function Evaluation |
CN112104609A (en) * | 2020-08-20 | 2020-12-18 | 电子科技大学 | Method for verifiable privacy-aware true phase discovery in a mobile crowd-sourcing awareness system |
CN112464174A (en) * | 2020-10-27 | 2021-03-09 | 华控清交信息科技(北京)有限公司 | Method and device for verifying multi-party secure computing software and device for verifying |
CN112787809A (en) * | 2020-12-31 | 2021-05-11 | 华南理工大学 | Efficient crowd sensing data stream privacy protection truth value discovery method |
-
2022
- 2022-09-13 CN CN202211109100.9A patent/CN115499186A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200304293A1 (en) * | 2017-08-30 | 2020-09-24 | Inpher, Inc. | High-Precision Privacy-Preserving Real-Valued Function Evaluation |
CN108494760A (en) * | 2018-03-14 | 2018-09-04 | 安徽大学 | A kind of intelligent perception true value discovery method of protection privacy |
CN112104609A (en) * | 2020-08-20 | 2020-12-18 | 电子科技大学 | Method for verifiable privacy-aware true phase discovery in a mobile crowd-sourcing awareness system |
CN112464174A (en) * | 2020-10-27 | 2021-03-09 | 华控清交信息科技(北京)有限公司 | Method and device for verifying multi-party secure computing software and device for verifying |
CN112787809A (en) * | 2020-12-31 | 2021-05-11 | 华南理工大学 | Efficient crowd sensing data stream privacy protection truth value discovery method |
Non-Patent Citations (1)
Title |
---|
冯琦: "基于安全多方计算的数据隐私保护技术研究", 中国博士学位论文全文数据库 信息科技辑, 15 August 2022 (2022-08-15), pages 1 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110189174A (en) | A kind of mobile intelligent perception motivational techniques based on quality of data perception | |
CN116167084A (en) | Federal learning model training privacy protection method and system based on hybrid strategy | |
CN112347500B (en) | Machine learning method, device, system, equipment and storage medium of distributed system | |
CN113992676A (en) | Incentive method and system for layered federal learning under terminal edge cloud architecture and complete information | |
CN114418109A (en) | Node selection and aggregation optimization system and method for federal learning under micro-service architecture | |
CN111814184A (en) | Differential privacy method for protecting mobile crowd sensing track privacy | |
CN116468556A (en) | Internet of things trust analysis method and system for electric power market frequency modulation transaction | |
CN116669111A (en) | Mobile edge computing task unloading method based on blockchain | |
CN115510482A (en) | Crowd sensing data privacy protection integrating self-adaptive differential privacy and federal learning | |
Aloqaily et al. | Fairness-aware game theoretic approach for service management in vehicular clouds | |
CN115021929B (en) | Trust management method and device for computing power network, storage medium and electronic equipment | |
CN116416067A (en) | Internet of things frequency modulation transaction information trust degree analysis method and system of gas motor unit | |
CN116596667A (en) | Internet of things trust analysis method and system for nuclear power unit frequency modulation transaction management | |
CN115759289A (en) | Federal learning method, system and device based on user grouping cooperation | |
CN116595094A (en) | Federal learning incentive method, device, equipment and storage medium based on block chain | |
Rizwan et al. | Intelligent digital twin for federated learning in aiot networks | |
Li et al. | Secure federated learning with efficient communication in vehicle network | |
US20230274183A1 (en) | Processing of machine learning modeling data to improve accuracy of categorization | |
Yang et al. | Edge computing and networking resource management for decomposable deep learning: An auction-based approach | |
CN116342287A (en) | Internet of things trust analysis method and system for thermal power generating unit frequency modulation transaction management | |
CN115499186A (en) | Privacy protection scheme based on secure multi-party calculation truth value discovery in mobile crowd sensing | |
CN116432040A (en) | Model training method, device and medium based on federal learning and electronic equipment | |
Guo et al. | B 2 sfl: A bi-level blockchained architecture for secure federated learning-based traffic prediction | |
Berta et al. | Dimension reduction methods for collaborative mobile gossip learning | |
CN113297310A (en) | Method for selecting block chain fragmentation verifier in Internet of things |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |