Adaptive Optimization of Deep Learning Models on AES based Large Side Channel Attack Data
Keywords:
Side-channel attacks, Deep Learning, Hyperparameters, Profiling models, OptimizersAbstract
Deep learning-based side-channel analysis is an efficient and suitable technique for profiling side-channel attacks. In order to obtain the better performance, it is highly necessary to analyze an in-depth training stage in which the optimization of relevant hyperparameters should be a vital process. During the training phase, hyperparameters that are connected to the architecture of the neural network are often selected; however, hyperparameters that impact the training process are to be effectively analyzed. This was represented by an optimized hyperparammeter that consists of considerable impact on attacking behaviour, which is the primary focus of our research. Our research has shown that even while the popular optimizers Adam and RMSprop are capable of delivering satisfactory outcomes, they are also tend to being overfit. Hence, it is necessary to use condensed training periods, simple profiling models, and explicit regularization in order to avoid this problem. On the other hand, the performance of optimizers of the SGD type is only satisfactory when momentum is used which results in slower convergence and less overfit. In conclusion, the research results provide a better use of Adagrad in the cases of longer training datasets or big profiling models.
References
H. Wang and E. Dubrova, "Tandem deep learning side-channel attack on FPGA implementation of AES," SN Computer Science, vol. 2, pp. 1-12, 2021.
K. Nomikos, A. Papadimitriou, M. Psarakis, A. Pikrakis, and V. Beroulle, "Evaluation of Hiding-based Countermeasures against Deep Learning Side Channel Attacks with Pre-trained Networks," in IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT), 2022, pp. 1-6: IEEE.
M. K. Hasan et al., "Lightweight cryptographic algorithms for guessing attack protection in complex internet of things applications," Complexity, vol. 2021, pp. 1-13, 2021.
A. A. Ahmed, M. K. Hasan, S. Islam, A. H. M. Aman, and N. Safie, "Design of Convolutional Neural Networks Architecture for Non-Profiled Side-Channel Attack Detection," Elektronika Ir Elektrotechnika, vol. 29, no. 4, pp. 76-81, 2023.
C. Dhasarathan et al., "COVID-19 health data analysis and personal data preserving: A homomorphic privacy enforcement approach," Computer communications, vol. 199, pp. 87-97, 2023.
C. Wang et al., "Portability of Deep-Learning Side-Channel Attacks against Software Discrepancies," in Proceedings of the 16th ACM Conference on Security and Privacy in Wireless and Mobile Networks, 2023, pp. 227-238.
A. A. Ahmed, R. A. Salim, and M. K. Hasan, "Deep Learning Method for Power Side-Channel Analysis on Chip Leakages," Elektronika ir Elektrotechnika, vol. 29, no. 6, pp. 50-57, 2023.
V.-P. Hoang, N.-T. Do, and V. S. Doan, "Performance Analysis of Deep Learning Based Non-profiled Side Channel Attacks Using Significant Hamming Weight Labeling," Mobile Networks Applications, pp. 1-10, 2023.
A. A. Ahmed and M. K. Hasan, "Design and Implementation of Side Channel Attack Based on Deep Learning LSTM," in IEEE Region 10 Symposium (TENSYMP), 2023, pp. 1-6: IEEE.
A. Ito, K. Saito, R. Ueno, and N. Homma, "Imbalanced data problems in deep learning-based side-channel attacks: Analysis and solution," IEEE Transactions on Information Forensics Security, vol. 16, pp. 3790-3802, 2021.
A. A. Ahmed et al., "Detection of Crucial Power Side Channel Data Leakage in Neural Networks," in 33rd International Telecommunication Networks and Applications Conference, 2023, pp. 57-62: IEEE.
S. Bhasin, A. Mendelson, and M. Nandi, "Security, Privacy, and Applied Cryptography Engineering: ," in 9th International Conference, SPACE 2019,, Gandhinagar, India, 2019, vol. 11947: Springer Nature.
A. A. Ahmed, M. K. Hasan, N. S. Nafi, A. H. Aman, S. Islam, and S. A. Fadhil, "Design of Lightweight Cryptography based Deep Learning Model for Side Channel Attacks," in 2023 33rd International Telecommunication Networks and Applications Conference, 2023, pp. 325-328: IEEE.
Y. Ou and L. Li, "Side-channel analysis attacks based on deep learning network," Frontiers of Computer Science, vol. 16, pp. 1-11, 2022.
D. Kwon, S. Hong, and H. Kim, "Optimizing implementations of non-profiled deep learning-based side-channel attacks," IEEE Access, vol. 10, pp. 5957-5967, 2022.
A. A. Ahmed, M. K. Hasan, N. S. Nafi, A. H. Aman, S. Islam, and M. S. Nahi, "Optimization Technique for Deep Learning Methodology on Power Side Channel Attacks," in 2023 33rd International Telecommunication Networks and Applications Conference, 2023, pp. 80-83: IEEE.
L. Zhang, X. Xing, J. Fan, Z. Wang, and S. Wang, "Multilabel deep learning-based side-channel attack," IEEE Transactions on Computer-Aided Design of Integrated Circuits Systems, vol. 40, no. 6, pp. 1207-1216, 2020.
H. Maghrebi, "Deep learning based side channel attacks in practice," Cryptology ePrint Archive, 2019.
N. T. Do, V. P. Hoang, V. S. Doan, and C. K. Pham, "On the performance of non‐profiled side channel attacks based on deep learning techniques," IET Information Security, vol. 17, no. 3, pp. 377-393, 2023.
D. Thapar, M. Alam, and D. Mukhopadhyay, "Transca: Cross-family profiled side-channel attacks using transfer learning on deep neural networks," Cryptology ePrint Archive, 2020.
L. Weissbart, "Performance analysis of multilayer perceptron in profiling side-channel analysis," in Applied Cryptography and Network Security Workshops: ACNS 2020 Satellite Workshops, AIBlock, AIHWS, AIoTS, Cloud S&P, SCI, SecMT, and SiMLA, Rome, Italy, 2020, pp. 198-216: Springer.
Li, Huimin, Marina Krček, and Guilherme Perin. "A comparison of weight initializers in deep learning-based side-channel analysis." Applied Cryptography and Network Security Workshops: ACNS 2020 Satellite Workshops, AIBlock, AIHWS, AIoTS, Cloud S&P, SCI, SecMT, and SiMLA, Rome, Italy, October 19–22, 2020, Proceedings 18. Springer International Publishing, 2020.
G. Perin and S. Picek, "On the Influence of Optimizers in Deep Learning-Based Side-Channel Analysis," in Selected Areas in Cryptography, Cham, 2021, pp. 615-636: Springer International Publishing.
H. Wang, M. Brisfors, S. Forsmark, and E. Dubrova, "How diversity affects deep-learning side-channel attacks," in IEEE Nordic Circuits and Systems Conference (NORCAS): NORCHIP and International Symposium of System-on-Chip (SoC), Helsinki, Finland, 2019, pp. 1-7: IEEE.
Wouters, Lennert, et al. "Revisiting a methodology for efficient CNN architectures in profiling attacks." IACR Transactions on Cryptographic Hardware and Embedded Systems (2020): 147-168.
G. Zaid, L. Bossuet, A. Habrard, and A. Venelli, "Efficiency through diversity in ensemble models applied to side-channel attacks:–a case study on public-key algorithms–," IACR Transactions on Cryptographic Hardware Embedded Systems, vol. 2021, no. 3, pp. 60-96, 2021.
T. Kubota, K. Yoshida, M. Shiozaki, and T. Fujino, "Deep learning side-channel attack against hardware implementations of AES," Microprocess. Microsyst., vol. 87, p. 103383, 2021.
S. Gupta et al., "A Novel Approach Toward the Prevention of the Side Channel Attacks for Enhancing the Network Security," no. Pre-print, 2022.
E. Cagli, C. Dumas, and E. Prouff, "Enhancing dimensionality reduction methods for side-channel attacks," in Smart Card Research and Advanced Applications: 14th International Conference, CARDIS 2015, Bochum, Germany, 2016, pp. 15-33: Springer.
M. Panoff, H. Yu, H. Shan, and Y. Jin, "A Review and Comparison of AI-enhanced Side Channel Analysis," ACM Journal on Emerging Technologies in Computing Systems, vol. 18, no. 3, pp. 1-20, 2022.
Y. Zhou and F.-X. Standaert, "S-box pooling: towards more efficient side-channel security evaluations," in International Conference on Applied Cryptography and Network Security, Rome, Italy, 2022, pp. 146-164: Springer.
S. Swaminathan, Ł. Chmielewski, G. Perin, and S. Picek, "Deep learning-based side-channel analysis against aes inner rounds," in International Conference on Applied Cryptography and Network Security, Rome, Italy, 2022, pp. 165-182: Springer.
L. Chang, Y. Wei, S. He, and X. Pan, "Research on Side-Channel Analysis Based on Deep Learning with Different Sample Data," Applied Sciences, vol. 12, no. 16, p. 8246, 2022.
