Physical Adversarial Attack Against LiDAR-Based 3D Perception via 2D Patches

Summary

This paper presents a model-guided digital-to-physical attack that fools LiDAR-based 3D perception using 2D specular reflective patches placed on existing objects. The authors exploit LiDAR's weakness with specular surfaces, grouping task-critical points into a few connected regions and mapping them to patch locations. The attack reduces accuracy across ten state-of-the-art models and reduces Moderate 3D AP for cars, pedestrians, and cyclists on the KITTI benchmark.

Topics

• Adversarial machine learning

Related items

• InfoImage watermarking robustness under MLLM-guided semantic editing: Benchmark, defense, and diagnosisSimilar attack · Elsevier Security Journals
• LowYour Robot's Safety Functions Already Work. What If the Input Lies?Similar attack · VicOne Blog
• InfoSpeech Tokenizers are Vulnerable: Transferable Semantic Attack and Robust TokenizerSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoAdversarial Retraining for Machine Learning-Based Man-in-the-Middle Attack Detection in Smart Grid Industrial Control SystemsSimilar attack · OpenAlex (peer-reviewed AI security)
• LowMeasuring Robustness and Efficiency in a Connectome-Constrained Fly Visual System Model: Linking an Adversarial and a Perceptual IllusionSimilar attack · Arxiv (cs.RO + cs.CV security)