arXiv AI October 31, 2026 By Alexandros Gkillas, Ioulia Kapsali, Christos Anagnostopoulos, Aris S. Lalos

LiDAR-SHIELD: A Fully Dockerized Adversarial Robustness Assessment Framework for LiDAR-Based 3D Perception Models

LiDAR-SHIELD is a fully Dockerized framework that provides a unified interface for testing LiDAR-based 3D perception models against adversarial attacks. It exposes any model through three lightweight HTTP endpoints (/info, /forward, /gradient), allowing easy integration of new models or datasets with a single loader function. The framework supports both 3D semantic segmentation and 3D object detection, incorporating state‑of‑the‑art attacks such as PGD, Square Attack, point perturbation, point removal, point injection, and LiDAttack to systematically reveal vulnerabilities across diverse LiDAR backbones.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Jul 2

Comprehensive Robustness Analysis of LiDAR-based 3D Object Detection in Autonomous Driving

Recent advancements in LiDAR-only 3D object detection have demonstrated improved detection accuracy over benchmark datasets. However, the adversarial robustness of these models remains untested.

agents computer-vision robotics benchmarks safety

arXiv Computer Vision

Sep 30

Mirage: a Clean-Label Backdoor against LiDAR 3D Object Detection

arXiv:2606.20752v2 Announce Type: replace Abstract: Deep neural network-based LiDAR 3D object detection serves as a critical perception component in safety-critical autonomous systems. However, recen...

By Ziba Parsons, Ang Li

agents computer-vision robotics benchmarks safety

arXiv Machine Learning

Sep 1

Adversarial Calibration Attack on Autonomous Vehicles

arXiv:2608.28778v1 Announce Type: cross Abstract: Autonomous vehicles (AVs) rely on accurate camera-LiDAR calibration for multimodal sensor fusion. In practice, calibration can drift due to vibration...

By Liangkai Liu, Qingzhao Zhang, Kang G. Shin

agents computer-vision robotics multimodal benchmarks safety

arXiv Machine Learning

Jul 14

Adversarially Guided Diffusion for LiDAR Range Image Synthesis

arXiv:2607. 09787v1 Announce Type: cross Abstract: LiDAR semantic segmentation is a key perception task in autonomous driving, where false predictions can affect downstream planning and safety-critical decision-making.

By Stavros Bouras, Antonios Makris, Alexandros Gkillas, Aris S. Lalos, Konstantinos Tserpes

agents diffusion computer-vision robotics safety

arXiv Computer Vision

Oct 21

Provisioning Robust and Efficient LiDAR Perception for Autonomous Driving

The paper presents a method for creating LiDAR-based 3D object detectors that remain accurate under point‑cloud corruptions while meeting strict latency and memory constraints. It achieves robustness by generating corrupted samples that mimic extreme weather and training detectors to focus on hard samples, guided by perturbation sensitivity estimated from an ensemble of seven heterogeneous detectors. Efficiency is improved by narrowing the network and using offline neighborhood‑density measurements to reduce the number of points processed at each sampling stage, resulting in significant gains in AP under corruption and reductions in inference latency and GPU memory usage across multiple datasets and detector architectures.

By Tingxu Han, Zijie Shen, An Guo, Lyuke Wang, Chunrong Fang, Zhenyu Chen, Wei Song

agents computer-vision robotics efficiency

arXiv AI

Jul 21

ALLUDE: A Unified Evaluation System for Configurable Attacks in Differentiable Environments

arXiv:2607. 17077v1 Announce Type: cross Abstract: Adversarial attacks against vision models like object detectors are often evaluated under limited conditions, leaving their performance under-characterized.

By Mansi Phute, Alexander Greenhalgh, Matthew Hull, Haoran Wang, Alec Helbling, ShengYun Peng, Elliott Faa, Willian Lunardi, Martin Andreoni, Wenke Lee, Duen Horng Chau

safety