Improved Hybrid Bagging Resampling Framework for Deep Learning-Based Side-Channel Analysis

被引:0
作者
Hameed, Faisal [1 ,2 ]
Ramesh, Sumesh Manjunath [1 ,2 ]
Alkhzaimi, Hoda [1 ,2 ]
机构
[1] NYU, Metrotech Ctr 5, Dept Elect & Comp Engn, Brooklyn, NY 11201 USA
[2] New York Univ Abu Dhabi, Emerging Adv Res Technol Secur & Cryptol Ctr, POB 129188, Abu Dhabi, U Arab Emirates
关键词
side-channel analysis; deep learning; hamming weight leakage; class imbalance;
D O I
10.3390/computers13080210
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
As cryptographic implementations leak secret information through side-channel emissions, the Hamming weight (HW) leakage model is widely used in deep learning profiling side-channel analysis (SCA) attacks to expose the leaked model. However, imbalanced datasets often arise from the HW leakage model, increasing the attack complexity and limiting the performance of deep learning-based SCA attacks. Effective management of class imbalance is vital for training deep neural network models to achieve optimized and improved performance results. Recent works focus on either improved deep-learning methodologies or data augmentation techniques. In this work, we propose the hybrid bagging resampling framework, a two-pronged strategy for tackling class imbalance in side-channel datasets, consisting of data augmentation and ensemble learning. We show that adopting this framework can boost attack performance results in a practical setup. From our experimental results, the SMOTEENN ensemble achieved the best performance in the ASCAD dataset, and the basic ensemble performed the best in the CHES dataset, with both contributing over 70% practical improvements in performance compared to the original imbalanced dataset, and accelerating practical attack space in comparison to the classical setup of the attack.
引用
收藏
页数:29
相关论文
共 49 条
[1]  
Ancona M, 2018, Arxiv, DOI arXiv:1711.06104
[2]  
[Anonymous], 2018, CHES CTF AISyLab Datasets
[3]  
[Anonymous], 2007, Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, DOI DOI 10.1145/1277741.1277927
[4]   Deep learning for side-channel analysis and introduction to ASCAD database [J].
Benadjila, Ryad ;
Prouff, Emmanuel ;
Strullu, Remi ;
Cagli, Eleonora ;
Dumas, Cecile .
JOURNAL OF CRYPTOGRAPHIC ENGINEERING, 2020, 10 (02) :163-188
[5]  
Bengio S., 2004, ICML 04, P23, DOI [DOI 10.1145/1015330.1015415, 10.1145/1015330.1015415., DOI 10.1145/1015330]
[6]   SMOTE: Synthetic minority over-sampling technique [J].
Chawla, Nitesh V. ;
Bowyer, Kevin W. ;
Hall, Lawrence O. ;
Kegelmeyer, W. Philip .
2002, American Association for Artificial Intelligence (16)
[7]   Combating the Impact of Jittering in UAV-based Sensing Systems Using Deep Denoising Network [J].
Chen, Wei ;
Chang, Deng-Kai ;
Chen, Yu-Jia .
2020 IEEE 92ND VEHICULAR TECHNOLOGY CONFERENCE (VTC2020-FALL), 2020,
[8]   Physical security in the post-quantum era A survey on side-channel analysis, random number generators, and physically unclonable functions [J].
Chowdhury, Sreeja ;
Covic, Ana ;
Acharya, Rabin Yu ;
Dupee, Spencer ;
Ganji, Fatemeh ;
Forte, Domenic .
JOURNAL OF CRYPTOGRAPHIC ENGINEERING, 2022, 12 (03) :267-303
[9]  
Feng Gao, 2021, 2021 7th International Conference on Computer and Communications (ICCC), P267, DOI 10.1109/ICCC54389.2021.9674477
[10]  
Fernández-Delgado M, 2014, J MACH LEARN RES, V15, P3133