Exploiting Support Vector Machine Algorithm to Break the Secret Key
Template attacks (TA) and support vector machine (SVM) are two effective methods in side channel attacks (SCAs). Almost all studies on SVM in SCAs assume the required power traces are sufficient, which also implies the number of profiling traces belonging to each class is equivalent. Indeed, in the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Spolecnost pro radioelektronicke inzenyrstvi
2018-04-01
|
| Series: | Radioengineering |
| Subjects: | |
| Online Access: | https://www.radioeng.cz/fulltexts/2018/18_01_0289_0298.pdf |
| _version_ | 1811270848610304000 |
|---|---|
| author | S. Hou Y. Zhou H. Liu N. Zhu |
| author_facet | S. Hou Y. Zhou H. Liu N. Zhu |
| author_sort | S. Hou |
| collection | DOAJ |
| description | Template attacks (TA) and support vector machine (SVM) are two effective methods in side channel attacks (SCAs). Almost all studies on SVM in SCAs assume the required power traces are sufficient, which also implies the number of profiling traces belonging to each class is equivalent. Indeed, in the real attack scenario, there may not be enough power traces due to various restrictions. More specifically, the Hamming Weight of the S-Box output results in 9 binomial distributed classes, which significantly reduces the performance of SVM compared with the uniformly distributed classes. In this paper, the impact of the distribution of profiling traces on the performance of SVM is first explored in detail. And also, we conduct Synthetic Minority Oversampling TEchnique (SMOTE) to solve the problem caused by the binomial distributed classes. By using SMOTE, the success rate of SVM is improved in the testing phase, and SVM requires fewer power traces to recover the key. Besides, TA is selected as a comparison. In contrast to what is perceived as common knowledge in unrestricted scenarios, our results indicate that SVM with proper parameters can significantly outperform TA. |
| first_indexed | 2024-04-12T22:09:47Z |
| format | Article |
| id | doaj.art-47f2780db80b4ccf9659320ad28c0e65 |
| institution | Directory Open Access Journal |
| issn | 1210-2512 |
| language | English |
| last_indexed | 2024-04-12T22:09:47Z |
| publishDate | 2018-04-01 |
| publisher | Spolecnost pro radioelektronicke inzenyrstvi |
| record_format | Article |
| series | Radioengineering |
| spelling | doaj.art-47f2780db80b4ccf9659320ad28c0e652022-12-22T03:14:48ZengSpolecnost pro radioelektronicke inzenyrstviRadioengineering1210-25122018-04-01271289298Exploiting Support Vector Machine Algorithm to Break the Secret KeyS. HouY. ZhouH. LiuN. ZhuTemplate attacks (TA) and support vector machine (SVM) are two effective methods in side channel attacks (SCAs). Almost all studies on SVM in SCAs assume the required power traces are sufficient, which also implies the number of profiling traces belonging to each class is equivalent. Indeed, in the real attack scenario, there may not be enough power traces due to various restrictions. More specifically, the Hamming Weight of the S-Box output results in 9 binomial distributed classes, which significantly reduces the performance of SVM compared with the uniformly distributed classes. In this paper, the impact of the distribution of profiling traces on the performance of SVM is first explored in detail. And also, we conduct Synthetic Minority Oversampling TEchnique (SMOTE) to solve the problem caused by the binomial distributed classes. By using SMOTE, the success rate of SVM is improved in the testing phase, and SVM requires fewer power traces to recover the key. Besides, TA is selected as a comparison. In contrast to what is perceived as common knowledge in unrestricted scenarios, our results indicate that SVM with proper parameters can significantly outperform TA.https://www.radioeng.cz/fulltexts/2018/18_01_0289_0298.pdfPower analysissupport vector machinesynthetic minority oversampling techniqueHamming Weight class |
| spellingShingle | S. Hou Y. Zhou H. Liu N. Zhu Exploiting Support Vector Machine Algorithm to Break the Secret Key Radioengineering Power analysis support vector machine synthetic minority oversampling technique Hamming Weight class |
| title | Exploiting Support Vector Machine Algorithm to Break the Secret Key |
| title_full | Exploiting Support Vector Machine Algorithm to Break the Secret Key |
| title_fullStr | Exploiting Support Vector Machine Algorithm to Break the Secret Key |
| title_full_unstemmed | Exploiting Support Vector Machine Algorithm to Break the Secret Key |
| title_short | Exploiting Support Vector Machine Algorithm to Break the Secret Key |
| title_sort | exploiting support vector machine algorithm to break the secret key |
| topic | Power analysis support vector machine synthetic minority oversampling technique Hamming Weight class |
| url | https://www.radioeng.cz/fulltexts/2018/18_01_0289_0298.pdf |
| work_keys_str_mv | AT shou exploitingsupportvectormachinealgorithmtobreakthesecretkey AT yzhou exploitingsupportvectormachinealgorithmtobreakthesecretkey AT hliu exploitingsupportvectormachinealgorithmtobreakthesecretkey AT nzhu exploitingsupportvectormachinealgorithmtobreakthesecretkey |