Revealing leakage locationin side-channel attack based on convolutional neural network visualizing

XIE Xin-yi; LIU Shuai; WANG Li-hui; LI Qing; YU Jun

Chinese

您当前的位置：

首页 >

文章列表页 >

Revealing leakage locationin side-channel attack based on convolutional neural network visualizing

更新时间：2026-09-04

- Revealing leakage locationin side-channel attack based on convolutional neural network visualizing
- Vol. 38, Issue 3, Pages: 1-7(2021)
- 作者机构：
  
  1. 上海复旦微电子集团股份有限公司,上海,200433
  2. 复旦大学专用集成电路与系统国家重点实验室机构,上海,201203
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2021
- 稿件说明：
移动端阅览
谢欣宜, 刘帅, 王立辉, 李清, 俞军. 基于卷积神经网络可视化的侧信道泄露区间定位[J]. 微电子学与计算机, 2021, 38(3): 1-7.

XIE Xin-yi, LIU Shuai, WANG Li-hui, et al. Revealing leakage locationin side-channel attack based on convolutional neural network visualizing[J]. 2021, 38(3): 1-7.
谢欣宜, 刘帅, 王立辉, 李清, 俞军. 基于卷积神经网络可视化的侧信道泄露区间定位[J]. 微电子学与计算机, 2021, 38(3): 1-7. DOI：

XIE Xin-yi, LIU Shuai, WANG Li-hui, et al. Revealing leakage locationin side-channel attack based on convolutional neural network visualizing[J]. 2021, 38(3): 1-7. DOI：

摘要

侧信道攻击中，泄露区间的定位对进一步提升攻击效果和芯片防护产生至关重要的作用.对于基于神经网络的模板攻击，由于神经网络是黑盒模型，使得泄露区间定位成为难题.本文通过改进加权梯度类激活映射(Grad-CAM)，提出一种新的可以定位功耗或电磁曲线泄露位置的方法WAvg-Grad-CAM.该方法利用梯度计算进行区间定位，计算输入曲线的不同位置对攻击成功的影响程度，从而可以准确地定位输入曲线的泄露区间.通过实验对比其他常见的可视化方法在模板攻击中的应用效果，发现其拥有曲线平滑和噪音小的优势.实验证明在泄露情况未知且不进行二阶曲线处理的情况下，即使网络成功率较低，也可以直接对带掩码实现的曲线进行精准定位.

Abstract

Locating leakage plays a vital role in further improving the attack success rate and countermeasure in side-channel attacks. For template attacks based on convolutional neural network

it is difficult to locate the leakage due to the invisibility of the network. This paper proposed a new method named WAvg-Grad-CAM to locate the leakage spot of side-channel traces

based on the ideal of Gradient-weighted Class Activation Mapping(Grad-CAM). This method applies gradient mapping to compute the attacking effectiveness of different positions on the input trace. According to the attacking effectiveness

the leakage position of the input trace can be precisely located. The experiment shows that this new method has advantages of smooth result and lower noise

compared with other common visualization methods. The result shows that this attack method can be used to localize the masked implementations precisely

without leakages combination processing and without knowledge of the implemented protections

even on the condition of low successful rate.

关键词

Keywords

references

CAGLI E, DUMAS C, PROUFF E. Convolutional neural networks with data augmentation against jitter-based countermeasures: profiling attacks without pre-processing[C]//Proceedings of the 19th International Conference on Cryptographic Hardware and Embedded Systems.Taipei, China: Springer, 2017: 45-68. DOI: 10.1007/978-3-319-66787-4_3.

ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]//Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland: Springer, 2014: 818-833. DOI: 10.1007/978-3-319-10590-1_53.

BHASIN S, DANGER J L, GUILLEY S, et al. NICV: normalized inter-class variance for detection of side-channel leakage[C]//Proceedings of the 2014International Symposium on Electromagnetic Compatibility. Tokyo, Japan: IEEE, 2014: 310-313.

MESSERGES T S. Using second-order power analysis to attack DPA resistant software[C]//Proceedings of the Second International Workshop on Cryptographic Hardware and Embedded Systems. Worcester, MA, USA: Springer, 2000: 238-251. DOI: 10.1007/3-540-44499-8_19.

GIERLICHS B, LEMKE-RUST K, PAAR C. Templates vs. stochastic methods: a performance analysis for side channel cryptanalysis[C]//Proceedings of the 8th International Workshopon Cryptographic Hardware and Embedded Systems.Yokohama, Japan: Springer, 2006: 15-29. DOI: 10.1007/11894063_2.

CHARI S, RAO J R, ROHATGI P. Template attacks[C]//Proceedings of the4th International Workshop Redwood Shores on Cryptographic Hardware and Embedded Systems.Redwood Shores, CA, USA: Springer, 2003: 13-28. DOI: 10.1007/3-540-36400-5_3.

ARCHAMBEAU C, PEETERS E, STANDAERT F X, et al.Template attacks in principal subspaces[C]//Proceedings of the 8th International Workshop on Cryptographic Hardware and Embedded Systems. Yokohama, Japan: Springer, 2006: 1-14. DOI: 10.1007/11894063_1.

SELVARAJU R R, COGSWELL M, DAS A, et al. GRAD-CAM: visual explanations from deep networks via gradient-based localization[C]//2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE, 2017: 618-626. DOI: 10.1109/ICCV.2017.74.

TIMON B. Non-profiled deep learning-based side-channel attacks with sensitivity analysis[J]. IACR Transactions on Cryptographic Hardware and Embedded Systems, 2019, 2019(2): 107-131. DOI: 10.13154/tches.v2019.i2. 107-131.

Views

123

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Steganography model guided by attention mechanism and improved dense convolution

Implementation and verification of a dual-chain power gating strategy for low power design

Design of ultra-low power real-time clock circuits

Simulation on the DC characteristics of double heterojunction p-GaN HEMT with AlN/GaN hybrid buffer layer

Lightweight countermeasures against Spectre attacks on the branch prediction unit

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰