Paper 2026/606

PD-Net: Learning Device-Invariant Representations for Heterogeneous Cross-Device Side-Channel Attacks

, School of Cyber Science and Engineering, Nanjing University of Science and Technology, China

Wei Cheng, School of Cyber Science and Engineering, Nanjing University of Science and Technology, China, LTCI, Télécom Paris, Institut Polytechnique de Paris, France

Yuejun Liu, School of Cyber Science and Engineering, Nanjing University of Science and Technology, China

Jingdian Ming, School of Cyber Science and Engineering, Nanjing University of Science and Technology, China

Yongbin Zhou, School of Cyber Science and Engineering, Nanjing University of Science and Technology, China, Institute of Information Engineering, Chinese Academy of Sciences, China

Abstract

Heterogeneous cross-device side-channel attacks remain a critical yet underexplored challenge, as models trained on one device often fail to generalize across architectures. This paper presents PD-Net, a domain generalization framework that learns device-invariant features by disentangling algorithmic content from device-specific style and aligning feature distributions using prototypical and Maximum Mean Discrepancy (MMD) losses. PD-Net is trained on nine heterogeneous source domains spanning ARM/AVR/FPGA and power/electromagnetic leakage modalities, including 32-bit ARM Cortex-M0/M1/M3/M4, 8-bit AVR ATmega (three series), and 128-bit Xilinx Virtex-5 FPGA, and evaluated in a zero-shot setting without target-specific adaptation. Experimental results demonstrate robust zero-shot cross-architecture transfers between 8-bit and 32-bit devices, with consistent gains over existing generalization and transfer-learning approaches. In particular, PD-Net delivers 29 successful attacks with only 10 divergences across 70 settings, markedly outperforming the state of the art, which succeeds in only 4 cases and diverges 19 times. To the best of our knowledge, this is the first domain generalization (DG)-based deep learning framework to systematically demonstrate practical zero-shot heterogeneous cross-device side-channel attacks.

@misc{cryptoeprint:2026/606,
      author = {Dalin He and Wei Cheng and Yuejun Liu and Jingdian Ming and Yongbin Zhou},
      title = {{PD}-Net: Learning Device-Invariant Representations for Heterogeneous Cross-Device Side-Channel Attacks},
      howpublished = {Cryptology {ePrint} Archive, Paper 2026/606},
      year = {2026},
      url = {https://eprint.iacr.org/2026/606}
}