边缘协作的轻量级安全区域建议网络

doi:10.11959/j.issn.1000-436x.2020186

Abstract

Abstract:

Aiming at the problem of image privacy leakage and computing efficiency in edge environment,a lightweight and secure region proposal network (SecRPN) was proposed.A series of secure computing protocols were designed based on the additive secret sharing scheme.Two non-collusive edge servers cooperate to perform calculation modules such as secure feature processing,secure anchor transformation,secure bounding-box correction,and secure non-maximum suppression.Theoretical analysis guarantees the correctness and security of SecRPN.The actual performance evaluation shows that SecRPN is outstanding in the computational cost and communication overhead compared with the existing works.

Key words: edge-collaborative, region proposal network, object detection, additive secret sharing, secure computing protocol

CLC Number:

TP309.2

Jinbo XIONG,Renwan BI,Qianxin CHEN,Ximeng LIU. Towards edge-collaborative,lightweight and secure region proposal network[J]. Journal on Communications, 2020, 41(10): 188-201.

Figures/Tables 9

协议	RPN^[17]	SecRCNN^[25]	SecRPN
SRU	$O (N \log N)$	$O (N L)$	$O (N)$
SST	$O (N \log N)$	$O (N M L)$	$O (N)$
SAT	$O (N \log N)$	—	$O (N)$
SBC	$O (N \log N)$	—	$O (N)$
SBF	$O (N \log N)$	—	$O (N)$
SDS	$O (N \log N)$	$O (N L \log N)$	$O (N \log N)$
SNMS	$O (N \log N)$	$O (N^{2} L)$	$O (N \log N)$

协议通信轮数/轮	通信开销	协议	通信轮数/轮	通信开销
SMul1	$2 ‖ N ‖$	SAT	6	$10 ‖ N ‖$
SExp1	$‖ N ‖$	SBC	24	$32 ‖ N ‖$
SComp3	$4 ‖ N ‖$	SBF	6	$8 ‖ N ‖$
SRU3	$4 ‖ N ‖$	SDS	1	$‖ N ‖$
SST3	$3 ‖ N ‖$	SNMS	2+13logN	$3 ‖ N ‖ + 18 ‖ N ‖ \log N$

References 32

[1]	LIU Y , MA X , SHU L ,et al. Internet of things for noise mapping in smart cities:state-of-the-art and future directions[J]. IEEE Network, 2020,34(4): 112-118.
[2]	XIONG J , REN J , CHEN L ,et al. Enhancing privacy and availability for data clustering in intelligent electrical service of IoT[J]. IEEE Internet of Things Journal, 2019,6(2): 1530-1540.
[3]	艾瑞咨询. 中国智能物联网（AIoT）白皮书[R].(2020-02-28)[2020-07-20].
	Iresearch.White paper on China’s artificial intelligent and Internet of things (AIoT)[R].(2020-02-28)[2020-07-20].
[4]	XIONG Z , LI W , HAN Q ,et al. Privacy-preserving auto-driving:a GAN-Based approach to protect vehicular camera data[C]// 2019 IEEE International Conference on Data Mining. Piscataway:IEEE Press, 2019: 668-677.
[5]	PéREZ-HERNáNDEZ F , TABIK S , LAMAS A ,et al. Object detection binary classifiers methodology based on deep learning to identify small objects handled similarly:application in video surveillance[J]. Knowledge-Based Systems, 20206(194):105590.
[6]	XIONG J B , CHEN X , YANG Q ,et al. A task-oriented user selection incentive mechanism in edge-aided mobile crowdsensing[J]. IEEE Transactions on Network Science and Engineering, 2019,doi:10.1109/TNSE.2019.2940958.
[7]	CHEN Q , TANG S , YANG Q ,et al. Cooper:cooperative perception for connected autonomous vehicles based on 3d point clouds[C]// 2019 IEEE 39th International Conference on Distributed Computing Systems. Piscataway :IEEE Press, 2019: 514-524.
[8]	CHEN Q , MA X , TANG S ,et al. F-cooper:feature based cooperative perception for autonomous vehicle edge computing system using 3D point clouds[C]// 4th ACM/IEEE Symposium on Edge Computing. New York:ACM Press, 2019: 88-100.
[9]	LIN L , LIAO X , JIN H ,et al. Computation offloading toward edge computing[J]. Proceedings of the IEEE, 2019,107(8): 1584-1607.
[10]	WANG X , HAN Y , LEUNG V ,et al. Convergence of edge computing and deep learning:a comprehensive survey[J]. IEEE Communications Surveys ＆ Tutorials, 2020,22(2): 869-904.
[11]	ZHAO Z , ZHENG P , XU S ,et al. Object detection with deep learning:a review[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019,30(11): 3212-3232.
[12]	REN J , GUO Y , ZHANG D ,et al. Distributed and efficient object detection in edge computing:challenges and solutions[J]. IEEE Network, 2018,32(6): 137-143.
[13]	NIKOUEI S , CHEN Y , SONG S ,et al. Real-time human detection as an edge service enabled by a lightweight CNN[C]// 2018 IEEE International Conference on Edge Computing. Piscataway:IEEE Press, 2018: 125-129.
[14]	ZHANG H , ZHANG Z , ZHANG L ,et al. Object tracking for a smart city using IoT and edge computing[J]. Sensors, 2019,19(9): 1987-2009.
[15]	GIRSHICK R , DONAHUE J , DARRELL T ,et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2014: 580-587.
[16]	SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition[J]. arXiv Preprint,arXiv:1409.1556, 2014
[17]	REN S , HE K , GIRSHICK R ,et al. Faster R-CNN:towards real-time object detection with region proposal networks[C]// Advances in Neural Information Processing Systems. Piscataway:IEEE Press, 2015: 91-99.
[18]	REDMON J , DIVVALA S , GIRSHICK R ,et al. You only look once:unified,real-time object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2016: 779-788.
[19]	XIONG J B , ZHAO M , BHUIYAN M ,et al. An AI-enabled three-party game framework for guaranteed data privacy in mobile edge crowdsensing of IoT[J]. IEEE Transactions on Industrial Informatics, 2019,doi:10.1109/TII.2019.2957130.
[20]	GENTRY C , . Fully homomorphic encryption using ideal lattices[C]// Proceedings of the 41th Annual ACM Symposium on Theory of Computing. New York:ACM Press, 2009: 169-178.
[21]	DOWLIN N , GILAD-BACHRACH R , LAINE K ,et al. Cryptonets:applying neural networks to encrypted data with high throughput and accuracy[C]// International Conference on Machine Learning. New York:ACM Press, 2016: 201-210.
[22]	HESAMIFARD E , TAKABI H , GHASEMI M . CryptoDL:deep neural networks over encrypted data[J]. arXiv Preprint,arXiv:1711.05189, 2017
[23]	JUVEKAR C , VAIKUNTANATHAN V , CHANDRAKASAN A . Gazelle:a low latency framework for secure neural network inference[C]// 27th USENIX Security Symposium. Berkeley:USENIX Association, 2018: 1651-1669.
[24]	HUANG K , LIU X M , FU S J ,et al. A lightweight privacy-preserving CNN feature extraction framework for mobile sensing[J]. IEEE Transactions on Dependable and Secure Computing, 2019,doi:10.1109/TDSC.2019.2913362.
[25]	LIU Y , MA Z , LIU X M ,et al. Privacy-preserving object detection for medical images with Faster R-CNN[J]. IEEE Transactions on Information Forensics and Security, 2019(10):1.
[26]	LI F H , LI H , NIU B ,et al. Privacy computing:concept,computing framework,and future development trends[J]. Engineering, 2019,5(6): 981-1192.
[27]	BELANOVI? P , LEESER M , . A library of parameterized floating-point modules and their use[C]// International Conference on Field Programmable Logic and Applications. Berlin:Springer, 2002: 657-666.
[28]	XIONG J B , BI R , ZHAO M ,et al. Edge-assisted privacy-preserving raw data sharing framework for connected autonomous vehicles[J]. IEEE Wireless Communications, 2020,27(3): 24-30.
[29]	BOGDANOV D , LAUR S , WILLEMSON J . Sharemind:a framework for fast privacy-preserving computations[C]// European Symposium on Research in Computer Security. Berlin:Springer, 2008: 192-206.
[30]	BOGDANOV D , NIITSOO M , TOFTETAL T ,et al. High-performance secure multi-party computation for data mining applications[J]. International Journal of Information Security, 2012,11(6): 403-418.
[31]	MA Z , LIU Y , LIU X ,et al. Privacy-preserving outsourced speech recognition for smart IoT devices[J]. IEEE Internet of Things Journal, 2019,6(5): 8406-8420.
[32]	EVERINGHAM M , VANGOOL L , WILLIAMS C ,et al. The PASCAL visual object classes challenge 2007(VOC2007)results[C]// International Conference on Computer Vision. Piscataway:IEEE Press, 2007: 1-24.

Metrics

Recommended 0

No Suggested Reading articles found!

网络层	计算开销/ms		倍数/倍	通信开销/MB
网络层	RPN^[17]	SecRPN	倍数/倍	通信开销/MB
3×3卷积	27.3	52.0	1.9	0
安全ReLU	20.9	178.5	8.5	14.84
逐点卷积	0.3	0.6	2.0	0
Softmax	0.9	3.0	3.3	0.39
锚变换	2.0	9.0	4.5	0.65
边界框裁剪	3.2	15.6	4.9	8.35
边界框过滤	1.0	2.1	2.1	2.09
NMS	24.8	59.8	2.4	0.89

网络	计算开销/s	倍数/倍	通信开销/MB
RPN	0.086 2	—	—
SecRCNN	5.776 0	67.0	37.66
SecRPN	0.340 7	4.0	27.21

Towards edge-collaborative,lightweight and secure region proposal network

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 32

Related Articles 8

Metrics

Recommended 0

[1]	Yurong LIAO, Haining WANG, Cunbao LIN, Yang LI, Yuqiang FANG, Shuyan NI. Research progress of deep learning-based object detection of optical remote sensing image [J]. Journal on Communications, 2022, 43(5): 190-203.
[2]	Jinbo XIONG, Yongjie ZHOU, Renwan BI, Liang WAN, Youliang TIAN. Towards edge-collaborative, lightweight and privacy-preserving classification framework [J]. Journal on Communications, 2022, 43(1): 127-137.
[3]	Jiujiu CHEN, Chunyan FENG, Caili GUO, Yang YANG, Qizheng SUN, Meiyi ZHU. Video semantics-driven resource allocation algorithm in Internet of vehicles [J]. Journal on Communications, 2021, 42(7): 1-11.
[4]	Linqiang CHEN,Quanxin YANG,Lifeng YUAN,Ye YAO,Zhen ZHANG,Guohua WU. Passive forensic based on spatio-temporal localization of video object removal tampering [J]. Journal on Communications, 2020, 41(7): 110-120.
[5]	Yu ZHAO,Jie YANG,Miao LIU,Jinlong SUN,Guan GUI. Federated learning based intelligent edge computing technique for video surveillance [J]. Journal on Communications, 2020, 41(10): 109-115.
[6]	Xin ZHOU,Xiaoxin HE,Changwen ZHENG. Radio signal recognition based on image deep learning [J]. Journal on Communications, 2019, 40(7): 114-125.
[7]	Zhe CHEN,Hui-bin WANG,Jie SHEN,Li-zhong XU. Light intensity, spectrum and polarization information fusion based underwater object detection [J]. Journal on Communications, 2013, 34(3): 192-198.
[8]	En-ce ZHOU,Chun-ping LIU,Ling-yan ZHANG,Sheng-rong GONG,Quan LIU. Foreground object detection based on time information window adaptive kernel density estimation [J]. Journal on Communications, 2011, 32(3): 106-115.