Skip to content
InfoResearchPeer-reviewed

MIST: Multi-Source Imperceptible Saliency-Guided Transferable Adversarial Attack Framework for LiDAR Point Cloud Perception in Remote Sensing

Published
Record updated
View JSON

Summary

MIST is a transfer-based adversarial attack framework for LiDAR point cloud perception in remote sensing, published in Remote Sensing on 2026-11-15. It fuses source-model gradients, local geometric variation and predictive uncertainty into a multi-source saliency score that allocates perturbations, using reverse control for displacement limits and intensity scaling for update strength. Evaluated on ModelNet40, ScanObjectNN, KITTI and Waymo, it improves cross-model transferability while preserving geometric imperceptibility.