Dòng
|
Nội dung
|
1
|
|
2
|
Efficient CNN - Based Profiled side Channel Attacks / Tran Ngoc Quy // Tạp chí Tin học và Điều khiển học = Journal of Computer Science And Cybernetics . - 2021. - tr. 3-24. - ISSN: 1813-9663
Ký hiệu phân loại (DDC): 006.3 Profiled side—channel attacks are now considered as a pawn-7:33} form of side channel attacks used to break the security of cryptographic devices. A recent line of Menard: has investigated a new profiled attack based on deep learning and many of them have used com/olivine neural network (CNN) as deep learning architecture for the attack. The effectiveness of the attack in greatiy irilzenced by the CNN architecture. However. the CNN architecture used for current profiled amen-2;: have often been based on image recognition fields. and choosing the right CNN architectures and pa:a:;eters for adaption to profiled attacks is still challenging. In this paper, we propose an efficient pureed attack for unprotected and masking-protected cryptographic devices based on two CNN arr-2.1: aft-g: es. Called CNNn, CNNd respectively. Both of CNN architecture parameters proposed in this pap-3: are based on the property of points of interest on the power trace and further determined 0:: {Le Gny \Yolf Optimization (GVVO) algorithm. To verify the proposed attacks, experiments were Cr".'7_1;z’~.i on a trace set collected from an Atmega8515 smart card when it performs AES-l‘lS en-grjgtaca. a DPA contest v4 dataset and the ASCAD public dataset. Số bản sách:
(0)
Tài liệu số:
(0)
|
3
|
Efficient Cnn—Based Profiled Side Channel Attacks / Tran Ngọc Quy, Nguyen Hong Quang // Tạp chí Tin học và Điều khiển học = Journal of Computer Science And Cybernetics . - 2021. - tr. 3-24. - ISSN: 1813-9663
Ký hiệu phân loại (DDC): 006.3 Profiled side—channel attacks are now considered as a pawn-7:33} form of side channel attacks used to break the security of cryptographic devices. A recent line of Menard: has investigated a new profiled attack based on deep learning and many of them have used com/olivine neural network (CNN) as deep learning architecture for the attack. The effectiveness of the attack in greatiy irilzenced by the CNN architecture. However. the CNN architecture used for current profiled amen-2;: have often been based on image recognition fields. and choosing the right CNN architectures and pa:a:;eters for adaption to profiled attacks is still challenging. In this paper, we propose an efficient pureed attack for unprotected and masking-protected cryptographic devices based on two CNN arr-2.1: aft-g: es. Called CNNn, CNNd respectively. Both of CNN architecture parameters proposed in this pap-3: are based on the property of points of interest on the power trace and further determined 0:: {Le Gny \Yolf Optimization (GVVO) algorithm. To verify the proposed attacks, experiments were Cr".'7_1;z’~.i on a trace set collected from an Atmega8515 smart card when it performs AES-l‘lS en-grjgtaca. a DPA contest v4 dataset and the ASCAD public dataset. Số bản sách:
(0)
Tài liệu số:
(1)
|
4
|
Some new results on automatic identification of Vietnamese folk songs cheo and quanho // Tạp chí Tin học và Điều khiển học = Journal of Computer Science And Cybernetics . - 2020. - tr. 32-52. - ISSN: 1813-9663
Ký hiệu phân loại (DDC): 398.809 The paper will present an overview of the classification of music genres that have been performed in Vietnam and abroad. For two types of very popular folk songs of Vietnam such as Cheo and Quanho, the paper describes the dataset and Gaussian Mixture Model (GMM) to perform the experiments on identifying some of these folk songs. The GMM used for experiment with 4 sets of parameters containing Mel Frequency Cepstral Coefficients (MFCC), energy, the first and the second derivatives of MFCC and energy, tempo, intensity, and fundamental frequency. The results showed that the parameters added to the MFCCs contributed significantly to the improvement of the identification accuracy with the appropriate values of Gaussian component number M. Our experiments also showed that, on average, the length of the excerpts was only 29.63% of the whole song for Cheo and 38.1% of the whole song for Quanho, the identification rate was only 3.1% and 2.33% less than the whole song for Cheo and Quanho, respectively. The identification of Cheo and Quanho was also tested with i-vectors. Số bản sách:
(0)
Tài liệu số:
(1)
|
|
|
|
|