SCA-CGAN:A New Side-Channel Attack Method for Imbalanced Small Samples

Simple item page
dc.contributor.authorWang, W
dc.contributor.authorWang, J. N.
dc.contributor.authorHu, F. L.
dc.contributor.authorNi, F.
dc.coverage.issue1cs
dc.coverage.volume32cs
dc.date.accessioned2023-10-11T07:07:10Z
dc.date.available2023-10-11T07:07:10Z
dc.date.issued2023-04cs
dc.description.abstractIn recent years, many deep learning and machine learning based side channel analysis (SCA) techniques have been proposed, most of which are based on the optimization of existing network models to improve the performance of SCA. However, in practice, the attacker often captures unbalanced and small samples of data due to various environmental factors that limit and interfere with the successful implementation of SCA. To address this problem, in this paper, we firstly introduced the Conditional Generation Adversarial Network (CGAN). We proposed a new model SCA-CGAN that combines SCA and CGAN. We used it to generate a specified number and class of simulated energy traces to expand and augment the original energy traces. Finally, we used the augmented data to implement SCA and achieved a good result. Through experiments on the unprotected ChipWhisperer (CW) data and the ASCAD jittered dataset, the results shown that the SCA using the augmented data is the most efficient, and the correct key is successfully recovered on both datasets. For the CW dataset, the model accuracy is improved by 20.75% and the traces number required to recover the correct key is reduced by about 79.5%. For the ASCAD jittered dataset, when the jitter is 0 and 50, the traces number required to recover the correct key is reduced by about 76.8% and 75.7% respectively.en
dc.formattextcs
dc.format.extent124-135cs
dc.format.mimetypeapplication/pdfen
dc.identifier.citationRadioengineering. 2023 vol. 32, č. 1, s. 124-135. ISSN 1210-2512cs
dc.identifier.doi10.13164/re.2023.0124en
dc.identifier.issn1210-2512
dc.identifier.urihttp://hdl.handle.net/11012/214302
dc.language.isoencs
dc.publisherSpolečnost pro radioelektronické inženýrstvícs
dc.relation.ispartofRadioengineeringcs
dc.relation.urihttps://www.radioeng.cz/fulltexts/2023/23_01_0124_0135.pdfcs
dc.rightsCreative Commons Attribution 4.0 International licenseen
dc.rights.accessopenAccessen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectDeep learning side channel analysisen
dc.subjectSCA-CGANen
dc.subjectunbalanced small samplesen
dc.subjectdata augmentationen
dc.titleSCA-CGAN:A New Side-Channel Attack Method for Imbalanced Small Samplesen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
eprints.affiliatedInstitution.facultyFakulta eletrotechniky a komunikačních technologiícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
23_01_0124_0135.pdf
Size:
3.13 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
2023/1