Green Learning-Based Signal-Level Detection of RIS Spoofing Attacks in Vehicular ISAC Systems
Abstract
Integrated sensing and communication (ISAC) enables wireless infrastructure to jointly support communication and environmental sensing, but also introduces new physical-layer security threats. A malicious reconfigurable intelligent surface (RIS) can manipulate its time-varying reflection phases to generate spoofing echoes and distort the sensing results of a roadside unit (RSU). Existing trajectory-level detectors rely on reconstructed sensing parameters and vehicle trajectories, making their performance dependent on upstream estimation accuracy. In this paper, we propose a signal-level Green Learning (GL) framework that directly detects RIS spoofing from matched-filtered RSU echoes. The proposed method combines two-stage Subspace Approximation with Adjusted Bias (SAAB), Discriminant Feature Test (DFT), and eXtreme Gradient Boosting (XGBoost) for spatial-temporal representation learning, feature selection, and classification, respectively. Simulation results show 99.335\% detection accuracy for a 32-element malicious RIS at −80 dBm receiver noise power. GL remains competitive with Long Short-Term Memory (LSTM) and bidirectional LSTM (BiLSTM) baselines while requiring only 0.1119 million floating-point operations (FLOPs), and also generalizes to previously unseen RIS sizes.
Related
- WAMS Operations in modern power systems: A median expectation-based state estimation approach for grid resilience towards cyber attacks
- FedPGT: Progressive Gradient Transmission for Vehicular Federated Learning over Time-Varying Channels
- Dynamic Trust-Driven Resilient Finite-/Fixed-Time Formation Control for Multi-UAV Systems with Input Saturation Against Sybil Attacks
- Design of Attack-Resilient Load Frequency Control for Hybrid Wind–Diesel Power Systems Under Hybrid Cyber Attacks
- Physics-Informed Neural Network-Based Detection of False Data Injection Attacks on FACTS-Assisted Wide-Area Fractional-Order Damping Controllers
BibTeX
@misc{chou2026green,
title = {{Green Learning-Based Signal-Level Detection of RIS Spoofing Attacks in Vehicular ISAC Systems}},
author = {Po-Heng Chou and Tingyu Shui and Pin-Qi Fu and Lien-Sheng Chang and Walid Saad and Li-Chun Wang},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.01881},
eprint = {2611.01881},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.01881},
}
RIS
TY - UNPB
TI - Green Learning-Based Signal-Level Detection of RIS Spoofing Attacks in Vehicular ISAC Systems
AU - Po-Heng Chou
AU - Tingyu Shui
AU - Pin-Qi Fu
AU - Lien-Sheng Chang
AU - Walid Saad
AU - Li-Chun Wang
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.01881
UR - https://arxiv.org/abs/2611.01881
AB - Integrated sensing and communication (ISAC) enables wireless infrastructure to jointly support communication and environmental sensing, but also introduces new physical-layer security threats. A malicious reconfigurable intelligent surface (RIS) can manipulate its time-varying reflection phases to generate spoofing echoes and distort the sensing results of a roadside unit (RSU). Existing trajectory-level detectors rely on reconstructed sensing parameters and vehicle trajectories, making their performance dependent on upstream estimation accuracy. In this paper, we propose a signal-level Green Learning (GL) framework that directly detects RIS spoofing from matched-filtered RSU echoes. The proposed method combines two-stage Subspace Approximation with Adjusted Bias (SAAB), Discriminant Feature Test (DFT), and eXtreme Gradient Boosting (XGBoost) for spatial-temporal representation learning, feature selection, and classification, respectively. Simulation results show 99.335\% detection accuracy for a 32-element malicious RIS at −80 dBm receiver noise power. GL remains competitive with Long Short-Term Memory (LSTM) and bidirectional LSTM (BiLSTM) baselines while requiring only 0.1119 million floating-point operations (FLOPs), and also generalizes to previously unseen RIS sizes.
ER -