会议论文集名称:
IEEE Congress on Evolutionary Computation
摘要:
Studies have shown that deep neural networks (DNNs) are susceptible to adversarial attacks, which can cause misclassification. The adversarial attack problem can be regarded as an optimization problem, then the genetic algorithm (GA) that is problem-independent can naturally be designed to solve the optimization problem to generate effective adversarial examples. Considering the dimensionality curse in the image processing field, traditional genetic algorithms in high-dimensional problems often fall into local optima. Therefore, we propose a GA with multiple fitness functions (MF-GA). Specifically, we divide the evolution process into three stages, i.e., exploration stage, exploitation stage, and stable stage. Besides, different fitness functions are used for different stages, which could help the GA to jump away from the local optimum. Experiments are conducted on three datasets, and four classic algorithms as well as the basic GA are adopted for comparisons. Experimental results demonstrate that MF-GA is an effective black-box attack method. Furthermore, although MF-GA is a black-box attack method, experimental results demonstrate the performance of MF-GA under the black-box environments is competitive when comparing to four classic algorithms under the white-box attack environments. This shows that evolutionary algorithms have great potential in adversarial attacks.
作者机构:
[Ning Z.] University of South China, Hengyang, China;[Si W.; Liao X.] Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China;[Tang Y.] University of South China, Hengyang, China, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
会议名称:
11th International Conference on Electronics, Communications and Networks, CECNet 2021
期刊:
E3S Web of Conferences,2021年293 ISSN:2267-1242
通讯作者:
Wang, Z.
作者机构:
[Zhang K.; Lv J.; Wang Z.; Yuan Z.; Li X.; Yi H.] School of Architecture, University of South China, Hengyang, 421001, China;[Bedra K.B.] School of Architecture and Art, Central South University, Changsha, 410083, China
通讯机构:
[Wang, Z.] S;School of Architecture, China
会议名称:
3rd Global Conference on Ecological Environment and Civil Engineering, GCEECE 2021
作者机构:
University of South China, Hunan, China;Hunan Medical Big Data International Sci.&Tech. Innovation Cooperation Base, Hunan, China;[Ma X.; Liu Y.; Ouyang C.] University of South China, Hunan, China, Hunan Medical Big Data International Sci.&Tech. Innovation Cooperation Base, Hunan, China
会议名称:
5th China Conference on Knowledge Graph, and Semantic Computing, CCKS 2020
会议时间:
12 November 2020 through 15 November 2020
关键词:
Event detection;Graph convolutional networks;Hybrid representation;Syntactic information
摘要:
BACKGROUND: Fiber tracking with diffusion-weighted MRI has become an essential tool for estimating in vivo brain white matter architecture. Fiber tracking results are sensitive to the choice of processing method and tracking criteria. PURPOSE: To assess the variability for an algorithm in group studies reproducibility is of critical context. However, reproducibility does not assess the validity of the brain connections. Phantom studies provide concrete quantitative comparisons of methods relative to absolute ground truths, yet do no capture variabilities because of in vivo physiological factors. The ISMRM 2017 TraCED challenge was created to fulfill the gap. STUDY TYPE: A systematic review of algorithms and tract reproducibility studies. SUBJECTS: Single healthy volunteers. FIELD STRENGTH/SEQUENCE: 3.0T, two different scanners by the same manufacturer. The multishell acquisition included b-values of 1000, 2000, and 3000 s/mm(2) with 20, 45, and 64 diffusion gradient directions per shell, respectively. ASSESSMENT: Nine international groups submitted 46 tractography algorithm entries each consisting 16 tracts per scan. The algorithms were assessed using intraclass correlation (ICC) and the Dice similarity measure. STATISTICAL TESTS: Containment analysis was performed to assess if the submitted algorithms had containment within tracts of larger volume submissions. This also serves the purpose to detect if spurious submissions had been made. RESULTS: The top five submissions had high ICC and Dice >0.88. Reproducibility was high within the top five submissions when assessed across sessions or across scanners: 0.87-0.97. Containment analysis shows that the top five submissions are contained within larger volume submissions. From the total of 16 tracts as an outcome relatively the number of tracts with high, moderate, and low reproducibility were 8, 4, and 4. DATA CONCLUSION: The different methods clearly result in fundamentally different tract structures at the more conservative specificity choices. Data and challenge infrastructure remain available for continued analysis and provide a platform for comparison. LEVEL OF EVIDENCE: 5 Technical Efficacy Stage: 1 J. Magn. Reson. Imaging 2020;51:234-249.
作者机构:
[Luo Q.; Li D.] School of Civil Engineering, University of South China, Hengyang, China;Engineering Lab of Hunan for the Technologies of Building Environment Control, University of South China, Hengyang, China;[Chen G.] School of Civil Engineering, University of South China, Hengyang, China, Engineering Lab of Hunan for the Technologies of Building Environment Control, University of South China, Hengyang, China
会议名称:
11th International Symposium on Heating, Ventilation and Air Conditioning, ISHVAC 2019