Non-profiled side-channel attack based on deep learning using picture trace
Over the years, deep learning algorithms have advanced a lot and any innovation in the algorithms are demonstrated and benchmarked for image classification. Several other field including side-channel analysis (SCA) have recently adopted deep learning with great success. In SCA, the deep learning alg...
| Main Authors: | , , , , |
|---|---|
| Format: | Journal Article |
| Language: | English |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/147153 |
| _version_ | 1826115941755256832 |
|---|---|
| author | Won, Yoo-Seung Han, Dong-Guk Jap, Dirmanto Bhasin, Shivam Park, Jong-Yeon |
| author_facet | Won, Yoo-Seung Han, Dong-Guk Jap, Dirmanto Bhasin, Shivam Park, Jong-Yeon |
| author_sort | Won, Yoo-Seung |
| collection | NTU |
| description | Over the years, deep learning algorithms have advanced a lot and any innovation in the algorithms are demonstrated and benchmarked for image classification. Several other field including side-channel analysis (SCA) have recently adopted deep learning with great success. In SCA, the deep learning algorithms are typically working with 1-dimensional (1-D) data. In this work, we propose a unique method to improve deep learning based side-channel analysis by converting the measurements from raw-trace of 1-dimension data based on float or byte data into picture-formatted trace that has information based on the data position. We demonstrate why 'Picturization' is more suitable for deep learning and compare how input and hidden layers interact for each raw (1-D) and picture form. As one potential application, we use a Binarized Neural Network (BNN) learning method that relies on a BNN's natural properties to improve variables. In addition, we propose a novel criterion for attack success or failure based on statistical confidence level rather than determination of a correct key using a ranking system. |
| first_indexed | 2024-10-01T04:03:20Z |
| format | Journal Article |
| id | ntu-10356/147153 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:03:20Z |
| publishDate | 2021 |
| record_format | dspace |
| spelling | ntu-10356/1471532021-03-27T20:11:34Z Non-profiled side-channel attack based on deep learning using picture trace Won, Yoo-Seung Han, Dong-Guk Jap, Dirmanto Bhasin, Shivam Park, Jong-Yeon Engineering::Computer science and engineering::Information systems::Information systems applications Deep Learning Binarized Neural Network Over the years, deep learning algorithms have advanced a lot and any innovation in the algorithms are demonstrated and benchmarked for image classification. Several other field including side-channel analysis (SCA) have recently adopted deep learning with great success. In SCA, the deep learning algorithms are typically working with 1-dimensional (1-D) data. In this work, we propose a unique method to improve deep learning based side-channel analysis by converting the measurements from raw-trace of 1-dimension data based on float or byte data into picture-formatted trace that has information based on the data position. We demonstrate why 'Picturization' is more suitable for deep learning and compare how input and hidden layers interact for each raw (1-D) and picture form. As one potential application, we use a Binarized Neural Network (BNN) learning method that relies on a BNN's natural properties to improve variables. In addition, we propose a novel criterion for attack success or failure based on statistical confidence level rather than determination of a correct key using a ranking system. Published version 2021-03-24T06:13:04Z 2021-03-24T06:13:04Z 2021 Journal Article Won, Y., Han, D., Jap, D., Bhasin, S. & Park, J. (2021). Non-profiled side-channel attack based on deep learning using picture trace. IEEE Access, 9, 22480-22492. https://dx.doi.org/10.1109/ACCESS.2021.3055833 2169-3536 0000-0002-5205-7530 0000-0003-1695-5103 0000-0002-3149-9401 0000-0002-6903-5127 https://hdl.handle.net/10356/147153 10.1109/ACCESS.2021.3055833 2-s2.0-85100793209 9 22480 22492 en IEEE Access © 2021 The Author(s). Published by IEEE. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/. application/pdf |
| spellingShingle | Engineering::Computer science and engineering::Information systems::Information systems applications Deep Learning Binarized Neural Network Won, Yoo-Seung Han, Dong-Guk Jap, Dirmanto Bhasin, Shivam Park, Jong-Yeon Non-profiled side-channel attack based on deep learning using picture trace |
| title | Non-profiled side-channel attack based on deep learning using picture trace |
| title_full | Non-profiled side-channel attack based on deep learning using picture trace |
| title_fullStr | Non-profiled side-channel attack based on deep learning using picture trace |
| title_full_unstemmed | Non-profiled side-channel attack based on deep learning using picture trace |
| title_short | Non-profiled side-channel attack based on deep learning using picture trace |
| title_sort | non profiled side channel attack based on deep learning using picture trace |
| topic | Engineering::Computer science and engineering::Information systems::Information systems applications Deep Learning Binarized Neural Network |
| url | https://hdl.handle.net/10356/147153 |
| work_keys_str_mv | AT wonyooseung nonprofiledsidechannelattackbasedondeeplearningusingpicturetrace AT handongguk nonprofiledsidechannelattackbasedondeeplearningusingpicturetrace AT japdirmanto nonprofiledsidechannelattackbasedondeeplearningusingpicturetrace AT bhasinshivam nonprofiledsidechannelattackbasedondeeplearningusingpicturetrace AT parkjongyeon nonprofiledsidechannelattackbasedondeeplearningusingpicturetrace |