{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T09:24:56Z","timestamp":1762161896360,"version":"build-2065373602"},"reference-count":33,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,4,27]],"date-time":"2025-04-27T00:00:00Z","timestamp":1745712000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62162016","62062026","J1-60012","J1-4084"],"award-info":[{"award-number":["62162016","62062026","J1-60012","J1-4084"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guilin University of Electronic Technology, China","award":["62162016","62062026","J1-60012","J1-4084"],"award-info":[{"award-number":["62162016","62062026","J1-60012","J1-4084"]}]},{"name":"Slovenian Research and Innovation Agency (ARIS)","award":["62162016","62062026","J1-60012","J1-4084"],"award-info":[{"award-number":["62162016","62062026","J1-60012","J1-4084"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>In deep learning-based side-channel analysis (DL-SCA), there may be a proliferation of model parameters as the number of trace power points increases, especially in the case of raw power traces. Determining how to design a lightweight deep learning model that can handle a trace with more power points and has fewer parameters and lower time costs for profiled SCAs appears to be a challenge. In this article, a DL-SCA model is proposed by introducing a non-trained DL technique called random convolutional kernels, which allows us to extract the features of leakage like using a transformer model. The model is then processed by a classifier with an attention mechanism, which finally outputs the probability vector for the candidate keys. Moreover, we analyze the performance and complexity of the random kernels and discuss how they work in theory. On several public AES datasets, the experimental results show that the number of required profiling traces and trainable parameters reduce, respectively, by over 70% and 94% compared with state-of-the-art works, while ensuring that the number of power traces required to recover the real key is acceptable. Importantly, differing from previous SCA models, our architecture eliminates the dependency between the feature length of power traces and the number of trainable parameters, which allows for the architecture to be applied to the case of raw power traces.<\/jats:p>","DOI":"10.3390\/info16050351","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T09:39:47Z","timestamp":1745833187000},"page":"351","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Lightweight Deep Learning Model for Profiled SCA Based on Random Convolution Kernels"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6917-6889","authenticated-orcid":false,"given":"Yu","family":"Ou","sequence":"first","affiliation":[{"name":"Guangxi Key Laboratory of Cryptography and Information Security, Guilin University of Electronic Technology, Guilin 541004, China"}]},{"given":"Yongzhuang","family":"Wei","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Cryptography and Information Security, Guilin University of Electronic Technology, Guilin 541004, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2894-3871","authenticated-orcid":false,"given":"Ren\u00e9","family":"Rodr\u00edguez-Aldama","sequence":"additional","affiliation":[{"name":"Famnit & IAM, University of Primorska, 6000 Koper, Slovenia"}]},{"given":"Fengrong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Cyber Engineering, Xidian University, Xi\u2019an 710071, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Kocher, P.C. (1996, January 18\u201322). Timing Attacks on Implementations of Diffie-Hellman, RSA, DSS, and Other Systems. Proceedings of the Advances in Cryptology\u2014CRYPTO\u201996, 16th Annual International Cryptology Conference, Santa Barbara, CA, USA.","DOI":"10.1007\/3-540-68697-5_9"},{"key":"ref_2","unstructured":"Kocher, P.C., Jaffe, J., and Jun, B. (1996, January 15\u201319). Differential power analysis. Proceedings of the Advances in Cryptology\u2014CRYPTO\u201999: 19th Annual International Cryptology Conference, Santa Barbara, CA, USA."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"de la Fe, S., Park, H.B., Sim, B.Y., Han, D.G., and Ferrer, C. (2021). Profiling Attack against RSA Key Generation Based on a Euclidean algorithm. Information, 12.","DOI":"10.3390\/info12110462"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Maghrebi, H., Portigliatti, T., and Prouff, E. (2016, January 14\u201318). Breaking Cryptographic Implementations Using Deep Learning Techniques. Proceedings of the Security, Privacy, and Applied Cryptography Engineering: 6th International Conference, Hyderabad, India.","DOI":"10.1007\/978-3-319-49445-6_1"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"148","DOI":"10.46586\/tches.v2019.i3.148-179","article-title":"Make Some Noise. Unleashing the Power of Convolutional Neural Networks for Profiled Side-channel Analysis","volume":"2019","author":"Kim","year":"2019","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1007\/s13389-019-00220-8","article-title":"Deep learning for side-channel analysis and introduction to ASCAD database","volume":"10","author":"Benadjila","year":"2020","journal-title":"J. Cryptogr. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Picek, S., Samiotis, I.P., Kim, J., Heuser, A., Bhasin, S., and Legay, A. (2018, January 15\u201319). On the Performance of Convolutional Neural Networks for Side-Channel Analysis. Proceedings of the Security, Privacy, and Applied Cryptography Engineering: 8th International Conference, Kanpur, India.","DOI":"10.1007\/978-3-030-05072-6_10"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"102078","DOI":"10.1016\/j.jocs.2023.102078","article-title":"A deep learning-based side channel attack model for different block ciphers","volume":"72","author":"Li","year":"2023","journal-title":"J. Comput. Sci."},{"key":"ref_9","first-page":"413","article-title":"The Best of Two Worlds: Deep Learning-assisted Template Attack","volume":"2022","author":"Wu","year":"2021","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"828","DOI":"10.46586\/tches.v2022.i4.828-861","article-title":"Exploring Feature Selection Scenarios for Deep Learning-based Side-Channel Analysis","volume":"2022","author":"Perin","year":"2022","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_11","first-page":"401","article-title":"Information Theory-based Evolution of Neural Networks for Side-channel Analysis","volume":"2023","author":"Acharya","year":"2023","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_12","unstructured":"Hajra, S., Chowdhury, S., and Mukhopadhyay, D. (2023, December 06). EstraNet: An Efficient Shift-Invariant Transformer Network for Side-Channel Analysis. Available online: https:\/\/eprint.iacr.org\/2023\/1860."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"50","DOI":"10.5755\/j02.eie.34650","article-title":"Deep Learning Method for Power Side-Channel Analysis on Chip Leakages","volume":"29","author":"Ahmed","year":"2023","journal-title":"Elektron. Elektrotechnika"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3018","DOI":"10.1109\/TIFS.2023.3273169","article-title":"A Guessing Entropy-Based Framework for Deep Learning-Assisted Side-Channel Analysis","volume":"18","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_15","unstructured":"Liu, A., Wang, A., Sun, S., Wei, C., Ding, Y., Wang, Y., and Zhu, L. (2024, January 15). CL-SCA: Leveraging Contrastive Learning for Profiled Side-Channel Analysis. Available online: https:\/\/eprint.iacr.org\/2024\/049."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3849","DOI":"10.1109\/TIFS.2023.3287728","article-title":"Label Correlation in Deep Learning-Based Side-Channel Analysis","volume":"18","author":"Wu","year":"2023","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1049\/iet-ifs.2019.0602","article-title":"Research on a high-order AES mask anti-power attack","volume":"14","author":"Ou","year":"2020","journal-title":"IET Inf. Secur."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1454","DOI":"10.1007\/s10618-020-00701-z","article-title":"ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels","volume":"34","author":"Dempster","year":"2020","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_19","unstructured":"Salehinejad, H., Wang, Y., Yu, Y., Jin, T., and Valaee, S. (2022). S-Rocket: Selective Random Convolution Kernels for Time Series Classification. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"677","DOI":"10.46586\/tches.v2021.i3.677-707","article-title":"Reinforcement learning for hyperparameter tuning in deep learning-based side-channel analysis","volume":"2021","author":"Rijsdijk","year":"2021","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_21","first-page":"1","article-title":"Methodology for efficient CNN architectures in profiling attacks","volume":"2020","author":"Zaid","year":"2020","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Gupta, P., Drees, J.P., and H\u00fcllermeier, E. (2024, January 14). Automated Side-Channel Attacks using Black-Box Neural Architecture Search. Available online: https:\/\/eprint.iacr.org\/2023\/093.","DOI":"10.1145\/3600160.3600161"},{"key":"ref_23","first-page":"6","article-title":"On random weights and unsupervised feature learning","volume":"2","author":"Saxe","year":"2011","journal-title":"ICML"},{"key":"ref_24","first-page":"209","article-title":"The Curse of Class Imbalance and Conflicting Metrics with Machine Learning for Side-channel Evaluations","volume":"2019","author":"Picek","year":"2019","journal-title":"IACR Trans. Cryptogr. Hardw. Embed. Syst."},{"key":"ref_25","unstructured":"Perin, G., Wu, L., and Picek, S. (2021, March 18). AISY\u2014Deep Learning-based Framework for Side-channel Analysis. Available online: https:\/\/eprint.iacr.org\/2021\/357."},{"key":"ref_26","unstructured":"Smith, L. (2018). A disciplined approach to neural network hyper-parameters: Part 1 \u2013 learning rate, batch size, momentum, and weight decay. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Smith, L., and Topin, N. (2018). Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates. arXiv.","DOI":"10.1117\/12.2520589"},{"key":"ref_28","first-page":"309","article-title":"On the Mathematical Foundations of Theoretical Statistics","volume":"222","author":"Fisher","year":"1922","journal-title":"Philos. Trans. R. Soc."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Saravanan, P., Kalpana, P., Preethisri, V., and Sneha, V. (2014, January 16\u201318). Power analysis attack using neural networks with wavelet transform as pre-processor. Proceedings of the 18th International Symposium on VLSI Design and Test, Coimbatore, India.","DOI":"10.1109\/ISVDAT.2014.6881059"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ai, J., Wang, Z., Zhou, X., and Ou, C. (2016, January 13\u201315). Improved wavelet transform for noise reduction in power analysis attacks. Proceedings of the 2016 IEEE International Conference on Signal and Image Processing (ICSIP), Beijing, China.","DOI":"10.1109\/SIPROCESS.2016.7888333"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"95381","DOI":"10.1109\/ACCESS.2023.3311370","article-title":"Autoscaled-Wavelet Convolutional Layer for Deep Learning-Based Side-Channel Analysis","volume":"11","author":"Bae","year":"2023","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Bilgin, B., and Fischer, J.B. (2019). Convolutional Neural Network Based Side-Channel Attacks in Time-Frequency Representations. Smart Card Research and Advanced Applications, Springer.","DOI":"10.1007\/978-3-030-15462-2"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Garg, A., and Karimian, N. (2021, January 7\u20138). Leveraging Deep CNN and Transfer Learning for Side-Channel Attack. Proceedings of the 2021 22nd International Symposium on Quality Electronic Design (ISQED), Santa Clara, CA, USA.","DOI":"10.1109\/ISQED51717.2021.9424305"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/5\/351\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:22:45Z","timestamp":1760030565000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/5\/351"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,27]]},"references-count":33,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["info16050351"],"URL":"https:\/\/doi.org\/10.3390\/info16050351","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2025,4,27]]}}}