Lightweight distributed deep learning on compressive measurements for internet of things

被引:0
|
作者
Hu, Guiqiang [1 ,3 ]
Hu, Yong [1 ]
Wu, Tao [1 ,2 ,3 ]
Zhang, Yushu [4 ]
Yuan, Shuai [5 ]
机构
[1] Chongqing Water Resources & Elect Engn Coll, Sch Big Data, Chongqing 402160, Peoples R China
[2] Chongqing Univ Posts & Telecommun, Sch Cybersecur & Informat Law, Chongqing 400065, Peoples R China
[3] Chongqing Municipal Key Lab Cyberspace & Informat, Chongqing, Peoples R China
[4] Nanjing Univ Aeronaut & Astronaut, Coll Comp Sci & Technol, Nanjing 210016, Jiangsu, Peoples R China
[5] Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu 611731, Peoples R China
关键词
Distributed deep learning; Compressive sensing; Chaotic system; Internet of things; RANDOM PROJECTIONS; LOW-OVERHEAD; SECURE;
D O I
10.1016/j.engappai.2024.109581
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this work, we investigate the problem of distributed deep learning in Internet of Things (IoT). The proposed learning framework is constructed in a fog-cloud computing architecture, so as to overcome the limitation of resource constrained IoT end device. Compressive Sensing (CS) is used as a lightweight encryption in the framework to preserve the privacy of training data. Specifically, a chaotic-based CS measurement matrix construction mechanism is applied in the system to save the storage and transmission costs. With this design, the computation overhead of the learning framework in IoT can be successfully offloaded from IoT end device to the fog nodes. Theoretical analysis demonstrates that our system can guarantee security of the raw data against chosen plaintext attack (CPA). Experimental and analysis results show that our privacy- preserving proposal can significantly reduce the communication costs and computation costs with only a negligible accuracy penalty (with classification accuracy 91% testing on MNIST dataset under compression rate 0.5) compared to traditional non-private federated learning schemes. Notably, due to the chaotic-based CS measurement matrix construction mechanism, the memory requirement of end device side can be significantly reduced. This makes our framework be very suitable for the IoT applications in which end devices are equipped with low-spec chips.
引用
收藏
页数:12
相关论文
共 50 条
  • [41] Deep Learning for Detection of Routing Attacks in the Internet of Things
    Yavuz, Furkan Yusuf
    Unal, Devrim
    Gul, Ensar
    INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2019, 12 (01) : 39 - 58
  • [42] DeepThink IoT: The Strength of Deep Learning in Internet of Things
    Divyansh Thakur
    Jaspal Kaur Saini
    Srikant Srinivasan
    Artificial Intelligence Review, 2023, 56 : 14663 - 14730
  • [43] Fog-Embedded Deep Learning for the Internet of Things
    Lyu, Lingjuan
    Bezdek, James C.
    He, Xuanli
    Jin, Jiong
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2019, 15 (07) : 4206 - 4215
  • [44] On deep reinforcement learning security for Industrial Internet of Things
    Liu, Xing
    Yu, Wei
    Liang, Fan
    Griffith, David
    Golmie, Nada
    COMPUTER COMMUNICATIONS, 2021, 168 : 20 - 32
  • [45] DeepThink IoT: The Strength of Deep Learning in Internet of Things
    Thakur, Divyansh
    Saini, Jaspal Kaur
    Srinivasan, Srikant
    ARTIFICIAL INTELLIGENCE REVIEW, 2023, 56 (12) : 14663 - 14730
  • [46] Toward Deep Transfer Learning in Industrial Internet of Things
    Liu, Xing
    Yu, Wei
    Liang, Fan
    Griffith, David
    Golmie, Nada
    IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (15) : 12163 - 12175
  • [47] Federated deep learning for anomaly detection in the internet of things
    Wang, Xiaofeng
    Wang, Yonghong
    Javaheri, Zahra
    Almutairi, Laila
    Moghadamnejad, Navid
    Younes, Osama S.
    COMPUTERS & ELECTRICAL ENGINEERING, 2023, 108
  • [48] Robotized application based on deep learning and Internet of Things
    Pascal, Carlos
    Raveica, Laura-Ofelia
    Panescu, Doru
    2018 22ND INTERNATIONAL CONFERENCE ON SYSTEM THEORY, CONTROL AND COMPUTING (ICSTCC), 2018, : 646 - 651
  • [49] Internet of Things Security Analytics and Solutions with Deep Learning
    Holbrook, Luke
    Alamaniotis, Miltiadis
    2019 IEEE 31ST INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2019), 2019, : 178 - 185
  • [50] Deep Learning for Detection of Routing Attacks in the Internet of Things
    Furkan Yusuf Yavuz
    Devrim Ünal
    Ensar Gül
    International Journal of Computational Intelligence Systems, 2018, 12 : 39 - 58