International Association for Cryptologic Research

International Association
for Cryptologic Research

CryptoDB

Paper: Cross-Device Profiled Side-Channel Attack with Unsupervised Domain Adaptation

Authors:
Pei Cao , School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
Chi Zhang , School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
Xiangjun Lu , School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
Dawu Gu , School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
Download:
DOI: 10.46586/tches.v2021.i4.27-56
URL: https://tches.iacr.org/index.php/TCHES/article/view/9059
Search ePrint
Search Google
Abstract: Deep learning (DL)-based techniques have recently proven to be very successful when applied to profiled side-channel attacks (SCA). In a real-world profiled SCA scenario, attackers gain knowledge about the target device by getting access to a similar device prior to the attack. However, most state-of-the-art literature performs only proof-of-concept attacks, where the traces intended for profiling and attacking are acquired consecutively on the same fully-controlled device. This paper reminds that even a small discrepancy between the profiling and attack traces (regarded as domain discrepancy) can cause a successful single-device attack to completely fail. To address the issue of domain discrepancy, we propose a Cross-Device Profiled Attack (CDPA), which introduces an additional fine-tuning phase after establishing a pretrained model. The fine-tuning phase is designed to adjust the pre-trained network, such that it can learn a hidden representation that is not only discriminative but also domain-invariant. In order to obtain domain-invariance, we adopt a maximum mean discrepancy (MMD) loss as a constraint term of the classic cross-entropy loss function. We show that the MMD loss can be easily calculated and embedded in a standard convolutional neural network. We evaluate our strategy on both publicly available datasets and multiple devices (eight Atmel XMEGA 8-bit microcontrollers and three SAKURA-G evaluation boards). The results demonstrate that CDPA can improve the performance of the classic DL-based SCA by orders of magnitude, which significantly eliminates the impact of domain discrepancy caused by different devices.
Video from TCHES 2021
BibTeX
@article{tches-2021-31310,
  title={Cross-Device Profiled Side-Channel Attack with Unsupervised Domain Adaptation},
  journal={IACR Transactions on Cryptographic Hardware and Embedded Systems},
  publisher={Ruhr-Universit├Ąt Bochum},
  volume={2021, Issue 4},
  pages={27-56},
  url={https://tches.iacr.org/index.php/TCHES/article/view/9059},
  doi={10.46586/tches.v2021.i4.27-56},
  author={Pei Cao and Chi Zhang and Xiangjun Lu and Dawu Gu},
  year=2021
}