作者机构:
[Xu, Xiangrui; Li, Yaqin; Yuan, Cao] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Peoples R China.
通讯机构:
[Yuan, Cao] W;Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430023, Peoples R China.
关键词:
Deep neural network;ownership verification;security and privacy;serial number;watermarking
摘要:
The power of deep learning and the enormous effort and money required to build a deep learning model makes stealing them a hugely worthwhile and highly lucrative endeavor. Worse still, model theft requires little more than a high-school understanding of computer functions, which ensures a healthy and vibrant black market full of choice for any would-be pirate. As such, estimating how many neural network models are likely to be illegally reproduced and distributed in future is almost impossible. Therefore, we propose an embedded & x2018;identity bracelet & x2019; for deep neural networks that acts as proof of a model & x2019;s owner. Our solution is an extension to the existing trigger-set watermarking techniques that embeds a post-cryptographic-style serial number into the base deep neural network (DNN). Called a DNN-SN, this identifier works like an identity bracelet that proves a network & x2019;s rightful owner. Further, a novel training method based on non-related multitask learning ensures that embedding the DNN-SN does not compromise model performance. Experimental evaluations of the framework confirm that a DNN-SN can be embedded into a model when training from scratch or in the student network component of Net2Net.
会议名称:
11th International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR) - Automatic Target Recognition and Navigation
会议时间:
NOV 02-03, 2019
会议地点:
Wuhan, PEOPLES R CHINA
会议主办单位:
[Xu, Xiangrui;Li, Yaqin;Gao, Yunlong;Yuan, Cao] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan, Hubei, Peoples R China.
会议论文集名称:
Proceedings of SPIE
关键词:
Deep neural network;identity number (ID);Ownership verification
摘要:
Amid the maturity of machine learning, deep neural networks are gradually applied in the business sector rather than be restricted in the laboratory. However, its intellectual property protection encounters a significant challenge. In this paper, we aim at embedding a unique identity number (ID) to the deep neural network for model ownership verification. To this end, a scheme of generating DNN ID is proposed, which is the criterion for model ownership verification. After embedding, the model can complete the original performance and own a unique ID of this model as well. DNN ID can only be generated by the owner to check the model authorship. We evaluate this method on MNIST. Experiment results demonstrate that the DNN ID can accurately verify the ownership of our trained model.
会议名称:
8th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)
会议时间:
SEP 11-12, 2016
会议地点:
Zhejiang Univ, Hangzhou, PEOPLES R CHINA
会议主办单位:
Zhejiang Univ
会议论文集名称:
International Conference on Intelligent Human-Machine Systems and Cybernetics
关键词:
segmentation;active contour;smoothing parameter;edge information
摘要:
Active contour model is one of the most popular image segmentation frameworks. Conventional active contour model requires the empirical adjustment of smoothing parameter in energy functional and the smoothing parameter for active contour is a challenging problem. In this paper, we propose an automated adjustment method for the smoothing parameter in region-based active contour models and thus a full automated segmentation method is obtained. In proposed active contour model, the region term is the same as that in traditional region-based active contour model, whereas the prior term in traditional region-based active contour model is substituted by gray statistic of edge image on the contour. Thus the evolution of contour has the same iteration form as that in traditional region-based active contour model. But a driving force from the edge information takes the role of smoothing term and the adjustment of smoothing parameter is avoided. Experimental results show the proposed model can obtain segmentation quality comparable to the those obtained by traditional region-based active contour model, without the cumbersome trial of smoothing parameter.
作者机构:
[Li, Yaqin; Gong, Cheng; Yuan, Cao] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan, Peoples R China.
会议名称:
6th International Conference on Electronic, Mechanical, Information and Management Society (EMIM)
会议时间:
APR 01-03, 2016
会议地点:
Shenyang, PEOPLES R CHINA
会议主办单位:
[Li, Yaqin;Yuan, Cao;Gong, Cheng] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan, Peoples R China.
会议论文集名称:
ACSR-Advances in Comptuer Science Research
关键词:
Online-teaching;PCI;FPGA;DSP
摘要:
These online-teaching database systems are generated from online transactions, emails, videos, audios, images. They are stored in databases grow massively and become difficult to capture, form, store, manage, share, analyze and visualize via typical database software tools. The adventure of large amount of data and real-time requirements presents great challenges using traditional desktop computers. In this paper, to tackle the specific problem with a critical requirement of 10ms for whole data processing pipeline, we proposed a high performance embedded system as opposed to personal computer. Peripheral Component Interconnect (PCI) for data transferring from computer to Field Programmable Gate Array (FPGA) is proposed to solve the problem, and a custom-designed dual-port dual-channel RAM to realize simultaneous data exchange and data processing which was implemented using a 6-core Digital Signal Processor (DSP). The hardware system was designed and tested the performance of individual modules as well as the integration of them as a whole. We reported a total time using such pipeline of 7.5ms, meeting the critical requirement and demonstrating its feasibility in practical application.
作者:
Zhang, Xiaoqing;Qiu, Lan*;Qian, Qiongfen;Li, Yaqin
期刊:
Journal of Computational Information Systems,2015年11(14):5251-5258 ISSN:1553-9105
通讯作者:
Qiu, Lan
作者机构:
[Zhang, Xiaoqing; Li, Yaqin] School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, 430023, China;[Qiu, Lan] Library, Wuhan University, Wuhan, 430070, China;[Qian, Qiongfen] Department 4, Air Force Early Warning Academy, Wuhan, 430019, China
摘要:
With the development of information and the integration of media, it has great practical significance and research value to build a digital learning environment based on the complicated electronic circuit. However, the complicated electronic circuit in real-time need a complex and expensive technology. In order to overcome the high cost and technology, an approach was proposed for simplifying generation by approximating the excitations with rectangular pulses, triangular pulses and cosine waves which can be implemented with a moderate cost in analogical electronics. In this work, we improved a novel approach based on genetic programming, The differences between theoretical excitation signals and the approximation driving pulses, related to their excitation effects, were minimized by genetic programming. From these results, the accuracy of simulation can be improved by the new approach, the difference between theoretical complicated digital signals and the new approach is reduced. A trade off is obtained between the costs of implementation of digital processing in digital learning environments.
通讯机构:
[Li, Yaqin] W;Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan, Peoples R China.
会议名称:
9th International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR) - Parallel Processing of Images and Optimization; and Medical Imaging Processing
期刊:
Proceedings of SPIE - The International Society for Optical Engineering,2015年9814 ISSN:0277-786X
通讯作者:
Li, Yaqin
作者机构:
[Wang, Xuan] Wuhan Polytech Univ, Coll Hlth Sci & Nursing, Wuhan, Peoples R China.;[Li, Yaqin; Li, Shigao] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan, Peoples R China.
通讯机构:
[Li, Yaqin] W;Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan, Peoples R China.
会议名称:
9th International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR) - Parallel Processing of Images and Optimization; and Medical Imaging Processing
会议时间:
OCT 31-NOV 01, 2015
会议地点:
Enshi, PEOPLES R CHINA
会议主办单位:
[Wang, Xuan] Wuhan Polytech Univ, Coll Hlth Sci & Nursing, Wuhan, Peoples R China.^[Li, Yaqin;Li, Shigao] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan, Peoples R China.
期刊:
Applied Mechanics and Materials,2014年721:56-61 ISSN:1662-7482
作者机构:
[Lei Qin; Yaqin Li; Kang Zhou] School of mathematics and computer,Wuhan Polytechnic University;[Lei Qin; Yaqin Li; Kang Zhou] School of automation,Huazhong University of Science and Technology
会议名称:
International Conference on Vehicle, Mechanical and Electrical Engineering
会议时间:
20141129-3
会议地点:
Wuhan
会议论文集名称:
Vehicle, mechanical and electrical engineering: Selected, peer reviewed papers from the 2014 International Conference on Sustainable Energy and Advanced Materials (ICVMEE 2014), November 29-30, 2014, Wuhan, China
关键词:
Vehicle Routing Problem;Artificial Fish School Algorithm;Coding
摘要:
Vehicle Routing Problem (VRP) is one of the core issue of logistics distribution, for traditional precision algorithms and heuristic algorithms had low accuracies or easily fell into local optimal solutions, it was difficult to obtain the optimal solution. This paper proposes a heuristic artificial fish school algorithm (HAFSA) for VRP, firstly, three-dimensional particle coding method is applied to vehicle routing code, and infeasible and inadequate artificial fish coding for heuristic repair, secondly HAFSA steps are given, finally the algorithm is tested through a simulative example. The experimental results show that compared with traditional genetic algorithm (GA) and particle swarm optimization (PSO), AFSA and their extension algorithms, HAFSA has a better performance in time and space cost and convergence.
期刊:
Applied Mechanics and Materials,2013年329:382-386 ISSN:1660-9336
作者机构:
[Li Y.Q.; Chen D.] School of Mathematic and Computer Science, Wuhan Polytechnic University, China;[Yuan C.] School of Computer and Software, Wuhan Vocational College of Software and Engineering, China
会议名称:
3rd International Conference on Intelligent Structure and Vibration Control, ISVC 2013
会议时间:
22 March 2013 through 24 March 2013
关键词:
Arbitrary waveform generator;Direct digital synthesizer;Hard system;Limited diffracting wave