CVApr 3, 2025

SLACK: Attacking LiDAR-based SLAM with Adversarial Point Injections

MILA
arXiv:2504.03089v11 citationsh-index: 2
Originality Highly original
AI Analysis

This addresses a critical security problem for autonomous vehicles by introducing a novel attack method on LiDAR-based SLAM, which is incremental as it builds on adversarial techniques but targets an unexplored area.

The paper tackles the vulnerability of LiDAR-based SLAM in autonomous vehicles to adversarial point injections, proposing SLACK, a deep generative adversarial model that achieves superior performance in degrading navigation and map quality while maintaining accurate scan quality on KITTI and CARLA-64 datasets.

The widespread adoption of learning-based methods for the LiDAR makes autonomous vehicles vulnerable to adversarial attacks through adversarial \textit{point injections (PiJ)}. It poses serious security challenges for navigation and map generation. Despite its critical nature, no major work exists that studies learning-based attacks on LiDAR-based SLAM. Our work proposes SLACK, an end-to-end deep generative adversarial model to attack LiDAR scans with several point injections without deteriorating LiDAR quality. To facilitate SLACK, we design a novel yet simple autoencoder that augments contrastive learning with segmentation-based attention for precise reconstructions. SLACK demonstrates superior performance on the task of \textit{point injections (PiJ)} compared to the best baselines on KITTI and CARLA-64 dataset while maintaining accurate scan quality. We qualitatively and quantitatively demonstrate PiJ attacks using a fraction of LiDAR points. It severely degrades navigation and map quality without deteriorating the LiDAR scan quality.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes