東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Blockchain-Empowered Secure Machine Learning and Applications.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Blockchain-Empowered Secure Machine Learning and Applications./
作者:	Wang, Qianlong.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	101 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
Contained By:	Dissertations Abstracts International83-05B.
標題:	Computer engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28829598
ISBN:	9798460400027

Blockchain-Empowered Secure Machine Learning and Applications.
Wang, Qianlong.

Blockchain-Empowered Secure Machine Learning and Applications. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 101 p.

Source: Dissertations Abstracts International, Volume: 83-05, Section: B.

Thesis (Ph.D.)--Case Western Reserve University, 2021.

This item must not be sold to any third party vendors.

In the big data era, one of the most critical applications is multiparty learning or federated learning, which allows different parties to collaborate with each other to obtain better learning models without sharing their own data. However, there are several main concerns about the current multiparty learning systems. First, most existing systems are distributed and need a central server to coordinate the learning process. However, such a central server can easily become a single point of failure and may not be trustworthy. Second, although quite a few schemes have been proposed to study Byzantine attacks, a very common and challenging kind of attack in distributed systems, they generally consider the scenario of learning a global model. However, in fact, all parties in multiparty learning usually have their own local models. The learning methods and security issues, in this case, are not fully explored. In this work, we propose a novel blockchain-empowered decentralized secure multiparty learning system with heterogeneous local models called BEMA. Particularly, we consider two types of Byzantine attacks, and carefully design "off-chain sample mining" and "on-chain mining" schemes to protect the security of the proposed system. We theoretically prove the system performance bound and resilience under Byzantine attacks. Simulation results show that the proposed system obtains comparable performance with that of conventional distributed systems, and bounded performance in the case of Byzantine attacks.Additionally, we apply blockchain in the smart transportation system to develop a novel application in Intelligent Connected Vehicles (ICVs). ICVs can provide smart, safe, and efficient transportation services and have attracted intensive attention recently. Obtaining timely and accurate traffic information is one of the most important problems in transportation systems, which would allow people to select fast routes and avoid congestions, thus saving their travel time on the road. Currently, the most popular way to obtain traffic information is to inquire about navigation agents, e.g., Apple map, and Google map. However, these navigation agents are essentially centralized systems, which are vulnerable to service congestions, a single point of failure, and attacks. Furthermore, users' privacy gets compromised as the agents can know their home and work addresses and hence their identities, track them in real-time, etc. In this work, we propose TrafficChain, a secure and privacy-preserving decentralized traffic information collection system on the blockchain, by taking advantage of fog/edge computing infrastructure. In particular, we employ a two-layer blockchain architecture in TrafficChain to improve system efficiency, design a privacy-preserving scheme to protect users' identities and travel traces, and devise LSTM based deep learning mechanisms that can de- fend against Byzantine attacks and Sybil attacks in our system. Furthermore, an incentive mechanism is designed to motivate users to participate in the system. Simulation results show that TrafficChain works very efficiently and is resilient to both Byzantine attacks and Sybil attacks.

ISBN: 9798460400027Subjects--Topical Terms:

621879
Computer engineering.
Subjects--Index Terms:

Deep learning

Blockchain-Empowered Secure Machine Learning and Applications.
LDR:04441nmm a2200409 4500 001 2343373
005 20220502104239.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798460400027
035 $a (MiAaPQ)AAI28829598
035 $a (MiAaPQ)OhioLINKcase1625183576139299
035 $a AAI28829598
040 $a MiAaPQ $c MiAaPQ
100 1 $a Wang, Qianlong. $3 3681927
245 1 0 $a Blockchain-Empowered Secure Machine Learning and Applications.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 101 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
500 $a Advisor: Li, Pan.
502 $a Thesis (Ph.D.)--Case Western Reserve University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a In the big data era, one of the most critical applications is multiparty learning or federated learning, which allows different parties to collaborate with each other to obtain better learning models without sharing their own data. However, there are several main concerns about the current multiparty learning systems. First, most existing systems are distributed and need a central server to coordinate the learning process. However, such a central server can easily become a single point of failure and may not be trustworthy. Second, although quite a few schemes have been proposed to study Byzantine attacks, a very common and challenging kind of attack in distributed systems, they generally consider the scenario of learning a global model. However, in fact, all parties in multiparty learning usually have their own local models. The learning methods and security issues, in this case, are not fully explored. In this work, we propose a novel blockchain-empowered decentralized secure multiparty learning system with heterogeneous local models called BEMA. Particularly, we consider two types of Byzantine attacks, and carefully design "off-chain sample mining" and "on-chain mining" schemes to protect the security of the proposed system. We theoretically prove the system performance bound and resilience under Byzantine attacks. Simulation results show that the proposed system obtains comparable performance with that of conventional distributed systems, and bounded performance in the case of Byzantine attacks.Additionally, we apply blockchain in the smart transportation system to develop a novel application in Intelligent Connected Vehicles (ICVs). ICVs can provide smart, safe, and efficient transportation services and have attracted intensive attention recently. Obtaining timely and accurate traffic information is one of the most important problems in transportation systems, which would allow people to select fast routes and avoid congestions, thus saving their travel time on the road. Currently, the most popular way to obtain traffic information is to inquire about navigation agents, e.g., Apple map, and Google map. However, these navigation agents are essentially centralized systems, which are vulnerable to service congestions, a single point of failure, and attacks. Furthermore, users' privacy gets compromised as the agents can know their home and work addresses and hence their identities, track them in real-time, etc. In this work, we propose TrafficChain, a secure and privacy-preserving decentralized traffic information collection system on the blockchain, by taking advantage of fog/edge computing infrastructure. In particular, we employ a two-layer blockchain architecture in TrafficChain to improve system efficiency, design a privacy-preserving scheme to protect users' identities and travel traces, and devise LSTM based deep learning mechanisms that can de- fend against Byzantine attacks and Sybil attacks in our system. Furthermore, an incentive mechanism is designed to motivate users to participate in the system. Simulation results show that TrafficChain works very efficiently and is resilient to both Byzantine attacks and Sybil attacks.
590 $a School code: 0042.
650 4 $a Computer engineering. $3 621879
650 4 $a Computer science. $3 523869
650 4 $a Automotive engineering. $3 2181195
650 4 $a Artificial intelligence. $3 516317
653 $a Deep learning
653 $a Intelligent Connected Vehicles
653 $a Byzantine attacks
653 $a Sybil attacks
653 $a Security
653 $a Privacy
690 $a 0984
690 $a 0464
690 $a 0800
690 $a 0540
710 2 $a Case Western Reserve University. $b EECS - Computer Engineering. $3 3560954
773 0 $t Dissertations Abstracts International $g 83-05B.
790 $a 0042
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28829598