20.500.12556/RUP-21799 A lightweight deep learning model for profiled SCA based on random convolution kernels 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. side-channel analysis deep learning convolution neural networks random convolution kernel analiza stranskih kanalov globoko učenje konvolucijska nevronska mreža naključno konvolucijsko jedro true false false Angleški jezik Slovenski jezik Članek v reviji 2025-09-26 12:24:25 2025-09-26 12:24:27 2025-10-17 03:04:10 0000-00-00 00:00:00 2025 0 0 str. 1-20 iss. 5, [article no.] 351 Vol. 16 May 2025 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 2025-04-27 004.7:004.8 2078-2489 10.3390/info16050351 234521859 RAZ_Ou_Yu_2025.pdf RAZ_Ou_Yu_2025.pdf 1 7CD2975FED8077F681AC93A093FB01FA a6a9ccb9f9b895b56fdaf5e491e12f73ead8b93a401b0a03473254f862f65495 3d16bfe6-9ac3-11f0-8f0b-005056ac49c0 https://repozitorij.upr.si/Dokument.php?lang=slv&id=31696 https://www.mdpi.com/2078-2489/16/5/351 1 1af2b24a-9ac3-11f0-8f0b-005056ac49c0 https://repozitorij.upr.si/Dokument.php?lang=slv&id=31695 Fakulteta za matematiko, naravoslovje in informacijske tehnologije 0 0 0