English

Physically-Guided Optical Inversion Enable Non-Contact Side-Channel Attack on Isolated Screens

Computer Vision and Pattern Recognition 2026-04-16 v1

Abstract

Noncontact exfiltration of electronic screen content poses a security challenge, with side-channel incursions as the principal vector. We introduce an optical projection side-channel paradigm that confronts two core instabilities: (i) the near-singular Jacobian spectrum of projection mapping breaches Hadamard stability, rendering inversion hypersensitive to perturbations; (ii) irreversible compression in light transport obliterates global semantic cues, magnifying reconstruction ambiguity. Exploiting passive speckle patterns formed by diffuse reflection, our Irradiance Robust Radiometric Inversion Network (IR4Net) fuses a Physically Regularized Irradiance Approximation (PRIrr-Approximation), which embeds the radiative transfer equation in a learnable optimizer, with a contour-to-detail cross-scale reconstruction mechanism that arrests noise propagation. Moreover, an Irreversibility Constrained Semantic Reprojection (ICSR) module reinstates lost global structure through context-driven semantic mapping. Evaluated across four scene categories, IR4Net achieves fidelity beyond competing neural approaches while retaining resilience to illumination perturbations.

Cite

@article{arxiv.2604.13419,
  title  = {Physically-Guided Optical Inversion Enable Non-Contact Side-Channel Attack on Isolated Screens},
  author = {Zhiwen Zheng and Yuheng Qiao and Xiaoshuai Zhang and Zhao Huang and Tao Zhang and Huiyu Zhou and Shaowei Jiang and Jin Liu and Wenwen Tang and Xingru Huang},
  journal= {arXiv preprint arXiv:2604.13419},
  year   = {2026}
}
R2 v1 2026-07-01T12:09:59.313Z