Neural Reconstruction of LiDAR Point Clouds under Jamming Attacks via Full-Waveform Representation and Simultaneous Laser Sensing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yoshida, Ryo, Sato, Takami, Zhang, Wenlun, Hayakawa, Yuki, Nagai, Shota, Kado, Takahiro, Beppu, Taro, Fujioka, Ibuki, Zhong, Yunshan, Yoshioka, Kentaro
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917376006553600
author Yoshida, Ryo
Sato, Takami
Zhang, Wenlun
Hayakawa, Yuki
Nagai, Shota
Kado, Takahiro
Beppu, Taro
Fujioka, Ibuki
Zhong, Yunshan
Yoshioka, Kentaro
author_facet Yoshida, Ryo
Sato, Takami
Zhang, Wenlun
Hayakawa, Yuki
Nagai, Shota
Kado, Takahiro
Beppu, Taro
Fujioka, Ibuki
Zhong, Yunshan
Yoshioka, Kentaro
contents LiDAR sensors are critical for autonomous driving perception, yet remain vulnerable to spoofing attacks. Jamming attacks inject high-frequency laser pulses that completely blind LiDAR sensors by overwhelming authentic returns with malicious signals. We discover that while point clouds become randomized, the underlying full-waveform data retains distinguishable signatures between attack and legitimate signals. In this work, we propose PULSAR-Net, capable of reconstructing authentic point clouds under jamming attacks by leveraging previously underutilized intermediate full-waveform representations and simultaneous laser sensing in modern LiDAR systems. PULSAR-Net adopts a novel U-Net architecture with axial spatial attention mechanisms specifically designed to identify attack-induced signals from authentic object returns in the full-waveform representation. To address the lack of full-waveform representations in existing LiDAR datasets under jamming attacks, we introduce a physics-aware dataset generation pipeline that synthesizes realistic full-waveform representations under jamming attacks. Despite being trained exclusively on synthetic data, PULSAR-Net achieves reconstruction rates of 92% and 73% for vehicles obscured by jamming attacks in real-world static and driving scenarios, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00371
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neural Reconstruction of LiDAR Point Clouds under Jamming Attacks via Full-Waveform Representation and Simultaneous Laser Sensing
Yoshida, Ryo
Sato, Takami
Zhang, Wenlun
Hayakawa, Yuki
Nagai, Shota
Kado, Takahiro
Beppu, Taro
Fujioka, Ibuki
Zhong, Yunshan
Yoshioka, Kentaro
Computer Vision and Pattern Recognition
LiDAR sensors are critical for autonomous driving perception, yet remain vulnerable to spoofing attacks. Jamming attacks inject high-frequency laser pulses that completely blind LiDAR sensors by overwhelming authentic returns with malicious signals. We discover that while point clouds become randomized, the underlying full-waveform data retains distinguishable signatures between attack and legitimate signals. In this work, we propose PULSAR-Net, capable of reconstructing authentic point clouds under jamming attacks by leveraging previously underutilized intermediate full-waveform representations and simultaneous laser sensing in modern LiDAR systems. PULSAR-Net adopts a novel U-Net architecture with axial spatial attention mechanisms specifically designed to identify attack-induced signals from authentic object returns in the full-waveform representation. To address the lack of full-waveform representations in existing LiDAR datasets under jamming attacks, we introduce a physics-aware dataset generation pipeline that synthesizes realistic full-waveform representations under jamming attacks. Despite being trained exclusively on synthetic data, PULSAR-Net achieves reconstruction rates of 92% and 73% for vehicles obscured by jamming attacks in real-world static and driving scenarios, respectively.
title Neural Reconstruction of LiDAR Point Clouds under Jamming Attacks via Full-Waveform Representation and Simultaneous Laser Sensing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.00371