计算机科学 ›› 2024, Vol. 51 ›› Issue (6A): 230700217-5.doi: 10.11896/jsjkx.230700217
臧洪睿, 杨婷婷, 刘洪波, 马凯
ZANG Hongrui, YANG Tingting, LIU Hongbo, MA Kai
摘要： 人工智能与物联网(Internet of Things,IoT)结合,可以改善物联网中应用的使用体验。在物联网中,数据共享可以改善应用的质量,但是同时也带来了数据安全问题,比如数据在共享过程中存在泄露和无法验证等问题。文中提出一种结合分布式联邦学习和区块链以及具备加密验证的方案,用来保护物联网中共享数据的隐私和数据的有效性。首先,利用联邦学习和区块链将物联网中由直接共享原始数据转化为共享加密的模型参数。接着,提出具备加密验证的方法,在模型聚合阶段对链上参数进行验证和挑选。最后,将所提方法与其他方法进行对比。实验结果表明,所提方法能够有效保证数据隐私并可以实现加密数据的验证,保证最终模型的精度,为物联网中数据高质量共享提供保障。
中图分类号:
| [1]JIA B,ZHANG X,LIU J,et al.Blockchain-enabled federatedlearning data protection aggregation scheme with differential privacy and homomorphic encryption in IIoT[J].IEEE Transactions on Industrial Informatics,2021,18(6):4049-4058. [2]FU L Y,LU G H,WU Y M,et al.Overview of Research and Development of Blockchain Technology[J].Computer Science,2022,49(S1):447-461. [3]MIAO Y,LIU Z,LI H,et al.Privacy-preserving Byzantine-ro-bust federated learning via blockchain systems[J].IEEE Transactions on Information Forensics and Security,2022,17:2848-2861. [4]SUN Z,WAN J,YIN L,et al.A blockchain-based audit ap-proach for encrypted data in federated learning[J].Digital Communications and Networks,2022,8(5):614-624 [5]BHAGOJI A N,CHAKRABORTY S,MITTAL P,et al.Analyzing federated learning through an adversarial lens[C]//International Conference on Machine Learning.PMLR,2019:634-643. [6]SHEN S,TOPLE S,SAXENA P.Auror:Defending against poisoning attacks in collaborative deep learning systems[C]//Proceedings of the 32nd Annual Conference on Computer Security Applications.2016:508-519. [7]QU X,WANG S,HU Q,et al.Proof of federated learning:A novel energy-recycling consensus algorithm[J].IEEE Transactions on Parallel and Distributed Systems,2021,32(8):2074-2085. [8]LIU Y,QU Y,XU C,et al.Blockchain-enabled asynchronousfederated learning in edge computing[J].Sensors,2021,21(10):3335. [9]LIU X,LI H,XU G,et al.Privacy-enhanced federated learning against poisoning adversaries[J].IEEE Transactions on Information Forensics and Security,2021,16:4574-4588. [10]LU Y,HUANG X,DAI Y,et al.Blockchain and FederatedLearning for Privacy-Preserved Data Sharing in Industrial IoT[J].IEEE Transactions on Industrial Informatics,2020,16(6):4177-4186. [11]QU X,WANG S,HU Q,et al.Proof of federated learning:A novel energy-recycling consensus algorithm[J].IEEE Transactions on Parallel and Distributed Systems,2021,32(8):2074-2085. [12]BLANCHARD P,EL MHAMDI E M,GUERRAOUI R,et al.Machine learning with adversaries:Byzantine tolerant gradient descent[J].Advances in Neural Information Processing Systems,2017,30:118-128. [13]FUNG C,YOON C J M,BESCHASTNIKH I.Mitigating sybils in federated learning poisoning[J].arXiv:1808.04866,2018. [14]ZHU L,LIU Z,HAN S.Deep leakage from gradients[J].Advances in Neural Information Processing Systems,2019,32:17-31. [15]ZHU H,WANG R,JINY,et al.Distributed Additive Encryption and Quantization for Privacy Preserving Federated Deep Lear-ning[J].Neurocomputing,2020,463:309-327. [16]ZHOU H,WORNELL G.Efficient homomorphic encryption on integer vectors and its applications[C]//2014 Information Theory and Applications Workshop(ITA).2014:1-9. [17]KETKAR N,SANTANA E.Deep learning with Python[M].Berkeley,CA:Apress,2017:97-111. [18]DILLON,JOSHUA V,et al.Tensorflow distributions[J].ar-Xiv:1711.10604,2017. [19]“Fiscobcos”[EB/OL].https://github.com/fisco-bcos. [20]AONO Y,HAYASHI T,WANG L,et al.Privacy-preserving deep learning via additively homomorphic encryption[J].IEEE Transactions on Information Forensics and Security,2017,13(5):1333-1345. |
|
||
首页