High-Efficiency Side-Channel Analysis: From Collaborative Denoising to Adaptive B-Spline Dimension Reduction

LUO Yuling; XU Haiyang; OUYANG Xue; FU Qiang; QIN Sheng; LIU Junxiu

doi:10.11999/JEIT251047

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2025 >

LUO Yuling, XU Haiyang, OUYANG Xue, FU Qiang, QIN Sheng, LIU Junxiu. High-Efficiency Side-Channel Analysis: From Collaborative Denoising to Adaptive B-Spline Dimension Reduction[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT251047

Citation:

LUO Yuling, XU Haiyang, OUYANG Xue, FU Qiang, QIN Sheng, LIU Junxiu. High-Efficiency Side-Channel Analysis: From Collaborative Denoising to Adaptive B-Spline Dimension Reduction[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT251047

Citation:

LUO Yuling, XU Haiyang, OUYANG Xue, FU Qiang, QIN Sheng, LIU Junxiu. High-Efficiency Side-Channel Analysis: From Collaborative Denoising to Adaptive B-Spline Dimension Reduction[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT251047

PDF( 8079 KB)

High-Efficiency Side-Channel Analysis: From Collaborative Denoising to Adaptive B-Spline Dimension Reduction

doi: 10.11999/JEIT251047 cstr: 32379.14.JEIT251047

1.
School of Electronic and Information Engineering/College of Integrated Circuits, Guangxi Normal University, Guilin 541004, China
2.
Guangxi Key Lab of Brain-inspired Computing and Intelligent Chips, Guilin 541004, China

Funds: The National Natural Science Foundation of China (62462009, 42501519), Guangxi Science and Technology Program Project: Guangxi Science and Technology Base and Talent Special Project (Gui Ke AD24010047), Guangxi Young Science and Technology Talent Project (GXYESS2025144)

Received Date: 2025-09-30
Accepted Date: 2025-12-22
Rev Recd Date: 2025-12-20

Available Online: 2026-01-04

Abstract

Abstract

Objective The performance of side-channel attacks is often constrained by the low signal-to-noise ratio of raw power traces, the masking of local leakage by redundant high-dimensional data, and the reliance on empirically chosen preprocessing parameters. Existing studies typically optimize individual stages, such as denoising or dimensionality reduction, in isolation, lack a unified framework, and fail to balance signal-to-noise ratio enhancement with the preservation of local leakage features. A unified analysis framework is therefore proposed to integrate denoising, adaptive parameter selection, and dimensionality reduction while preserving local leakage characteristics. Through coordinated optimization of these components, both the efficiency and robustness of side-channel attacks are improved. Methods Based on the similarity of power traces corresponding to identical plaintexts and the local approximation properties of B-splines, a side-channel analysis method combining collaborative denoising and Adaptive B-Spline Dimension Reduction (ABDR) is presented. First, a Collaborative Denoising Framework (CDF) is constructed, in which high-quality traces are selected using a plaintext-mean template, and targeted denoising is performed via singular value decomposition guided by a singular-value template. Second, a Neighbourhood Asymmetry Clustering (NAC) method is applied to adaptively determine key thresholds within the CDF. Finally, an ABDR algorithm is proposed, which allocates knots non-uniformly according to the variance distribution of power traces, thereby enabling efficient data compression while preserving critical local leakage features. Results and Discussions Experiments conducted on two datasets based on 8-bit AVR (OSR2560) and 32-bit ARM Cortex-M4 (OSR407) architectures demonstrate that the CDF significantly enhances the signal-to-noise ratio, with improvements of 60% on OSR2560 (Fig. 2) and 150% on OSR407 (Fig. 4). The number of power traces required for successful key recovery is reduced from 3 000/2 400 to 1 200/1 500 for the two datasets, respectively (Figs. 3 and 5). Through adaptive threshold selection in the CDF, NAC achieves faster and more stable guessing-entropy convergence than fixed-threshold and K-means-based strategies, which enhances overall robustness (Fig. 6). The ABDR algorithm places knots densely in high-variance leakage regions and sparsely in low-variance regions. While maintaining a high attack success rate, it reduces the data dimensionality from 5 000 and 5 500 to 1 000 and 500, respectively, corresponding to a compression rate of approximately 80%. At the optimal dimensionality (Fig. 7), the correlation coefficients of the correct key reach 0.186 0 on OSR2560 and 0.360 5 on OSR407, both exceeding those obtained using other dimensionality reduction methods. These results indicate superior local information retention and attack efficiency (Tables 3 and 4). Conclusions The results confirm that the proposed CDF substantially improves the signal-to-noise ratio of power traces, while NAC enables adaptive parameter selection and enhances robustness. Through accurate local modeling, ABDR effectively alleviates the trade-off between high-dimensional data reduction and the preservation of critical leakage information. Comprehensive experimental validation shows that the integrated framework addresses key challenges in side-channel analysis, including low signal-to-noise ratio, redundancy-induced information masking, and dependence on empirical parameters, and provides a practical and scalable solution for real-world attack scenarios.

FullText(HTML)

References(22)

References

[1]	ARPAIA P, CAPUTO F, CIOFFI A, et al. Uncertainty analysis in cryptographic key recovery for machine learning-based power measurements attacks[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1006108. doi: 10.1109/TIM.2023.3284933.
[2]	PANTOJA J J, BUCHELI V A, and DONALDSON R. Electromagnetic side-channel attack risk assessment on a practical quantum-key-distribution receiver based on multi-class classification[J]. EPJ Quantum Technology, 2024, 11(1): 78. doi: 10.1140/epjqt/s40507-024-00290-6.
[3]	MAJI S, BANERJEE U, and CHANDRAKASAN A P. Leaky nets: Recovering embedded neural network models and inputs through simple power and timing side-channels—Attacks and defenses[J]. IEEE Internet of Things Journal, 2021, 8(15): 12079–12092. doi: 10.1109/JIOT.2021.3061314.
[4]	RAEKER-JORDAN N, CHUNG J, KONG Zhenyu, et al. Ensuring additive manufacturing quality and cyber–physical security via side-channel measurements and transmissions[J]. Journal of Manufacturing Systems, 2024, 73: 275–286. doi: 10.1016/j.jmsy.2024.02.005.
[5]	LIU A, WANG An, SUN Shaofei, et al. CL-SCA: A contrastive learning approach for profiled side-channel analysis[J]. IEEE Transactions on Information Forensics and Security, 2025, 20: 5109–5122. doi: 10.1109/TIFS.2025.3570123.
[6]	KOCHER P, JAFFE J and JUN B. Differential power analysis[C]. The 19th Annual International Cryptology Conference (CRYPTO 1999), Santa Barbara, USA, 1999: 388–397. doi: 10.1007/3-540-48405-1_25.
[7]	WU Lichao, PERIN G, and PICEK S. Weakly profiling side-channel analysis[J]. IACR Transactions on Cryptographic Hardware and Embedded Systems, 2024, 2024(3): 707–730. doi: 10.46586/tches.v2024.i3.707-730.
[8]	YOU Chunheng, CHIANG C H, CHAO P C P, et al. New adaptive template attacks against Montgomery-ladder-based ECCs in IoT devices[J]. IEEE Internet of Things Journal, 2024, 11(12): 22716–22725. doi: 10.1109/JIOT.2024.3384076.
[9]	WU Lichao, WEISSBART L, KRČEK M, et al. Label correlation in deep learning-based side-channel analysis[J]. IEEE Transactions on Information Forensics and Security, 2023, 18: 3849–3861. doi: 10.1109/TIFS.2023.3287728.
[10]	GAO Pengfei, SONG Fu, and CHEN Taolue. Compositional verification of first-order masking countermeasures against power side-channel attacks[J]. ACM Transactions on Software Engineering and Methodology, 2024, 33(3): 79. doi: 10.1145/3635707.
[11]	DUCHARME G R and MAURINE P. Estimating the Signal-to-Noise ratio under repeated sampling of the same centered signal: Applications to side-channel attacks on a cryptoprocessor[J]. IEEE Transactions on Information Theory, 2018, 64(9): 6333–6339. doi: 10.1109/TIT.2018.2851217.
[12]	MOZIPO A T and ACKEN J M. Analysis of countermeasures against remote and local power side channel attacks using correlation power analysis[J]. IEEE Transactions on Dependable and Secure Computing, 2024, 21(6): 5128–5142. doi: 10.1109/TDSC.2024.3370711.
[13]	OU Changhai, LAM S K, SUN Degang, et al. SNR-centric power trace extractors for side-channel attacks[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2021, 40(4): 620–632. doi: 10.1109/TCAD.2020.3003849.
[14]	DEL POZO S M and STANDAERT F X. Blind source separation from single measurements using singular spectrum analysis[C]. The 17th International Workshop on Cryptographic Hardware and Embedded Systems (CHES 2015), Saint-Malo, France, 2015: 42–59. doi: 10.1007/978-3-662-48324-4_3.
[15]	ZHANG Fan, DONG Xiaofei, YANG Bolin, et al. A systematic evaluation of wavelet-based attack framework on random delay countermeasures[J]. IEEE Transactions on Information Forensics and Security, 2020, 15: 1407–1422. doi: 10.1109/TIFS.2019.2941774.
[16]	WANG Yuanzhen, ZHANG Hongxin, FANG Xing, et al. Hybrid threshold denoising framework using singular value decomposition for side-channel analysis preprocessing[J]. Entropy, 2023, 25(8): 1133. doi: 10.3390/e25081133.
[17]	LIU Songran and YI Wang. Task parameters analysis in schedule-based timing side-channel attack[J]. IEEE Access, 2020, 8: 157103–157115. doi: 10.1109/ACCESS.2020.3019323.
[18]	PENG Dehua, GUI Zhipeng, WANG Dehe, et al. Clustering by measuring local direction centrality for data with heterogeneous density and weak connectivity[J]. Nature Communications, 2022, 13(1): 5455. doi: 10.1038/s41467-022-33136-9.
[19]	PAGUADA S, BATINA L, and ARMENDARIZ I. Toward practical autoencoder-based side-channel analysis evaluations[J]. Computer Networks, 2021, 196: 108230. doi: 10.1016/j.comnet.2021.108230.
[20]	KONG Yinan and SAEEDI E. The investigation of neural networks performance in side-channel attacks[J]. Artificial Intelligence Review, 2019, 52(1): 607–623. doi: 10.1007/s10462-018-9640-4.
[21]	MAGHREBI H and PROUFF E. On the use of independent component analysis to denoise side-channel measurements[C]. The 9th International Workshop on Constructive Side-Channel Analysis and Secure Design (COSADE 2018), Singapore, Singapore, 2018: 61–81. doi: 10.1007/978-3-319-89641-0_4.
[22]	RIOJA U, BATINA L, FLORES J L, et al. Auto-tune POIs: Estimation of distribution algorithms for efficient side-channel analysis[J]. Computer Networks, 2021, 198: 108405. doi: 10.1016/j.comnet.2021.108405.