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

2026-03-31

AI Summary

This study addresses the degradation of LiDAR point clouds caused by high-frequency laser pulse interference. To tackle this issue, the authors propose a novel U-Net architecture augmented with an axial spatial attention mechanism, leveraging full-waveform data and synchronized laser sensing information to reconstruct authentic point clouds from corrupted signals. The key innovation lies in utilizing full-waveform representations to effectively discriminate between adversarial interference and genuine return echoes, alongside a physically grounded synthetic data generation pipeline. Remarkably, the model is trained exclusively on synthetic data yet achieves high reconstruction performance in real-world scenarios: it recovers 92% of occluded vehicle points in static scenes and 73% in dynamic settings, demonstrating strong generalization across diverse interference conditions.

Abstract

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.

Problem

• LiDAR
• jamming attacks
• spoofing attacks
• point cloud reconstruction
• autonomous driving

Innovation

• full-waveform representation
• LiDAR jamming attack
• neural point cloud reconstruction
• simultaneous laser sensing
• physics-aware synthetic dataset