D-SLAMSpoof: An Environment-Agnostic LiDAR Spoofing Attack using Dynamic Point Cloud Injection

• URL: http://arxiv.org/abs/2603.11365v1
• Date: Wed, 11 Mar 2026 23:06:52 GMT
• Title: D-SLAMSpoof: An Environment-Agnostic LiDAR Spoofing Attack using Dynamic Point Cloud Injection
• Abstract summary: We introduce Dynamic SLAMSpoof (D-SLAMSpoof), a novel attack that compromises LiDAR SLAM even in feature-rich environments.<n>D-SLAMSpoof significantly improves attack success rates in real-world, feature-rich environments such as urban areas and indoor spaces.<n>We propose a practical defense method, ISD-SLAM, that relies solely on inertial dead reckoning signals commonly available in autonomous systems.
• Score: 5.775959675362423
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we introduce Dynamic SLAMSpoof (D-SLAMSpoof), a novel attack that compromises LiDAR SLAM even in feature-rich environments. The attack leverages LiDAR spoofing, which injects spurious measurements into LiDAR scans through external laser interference. By designing both spatial injection shapes and temporally coordinated dynamic injection patterns guided by scan-matching principles, D-SLAMSpoof significantly improves attack success rates in real-world, feature-rich environments such as urban areas and indoor spaces, where conventional LiDAR spoofing methods often fail. Furthermore, we propose a practical defense method, ISD-SLAM, that relies solely on inertial dead reckoning signals commonly available in autonomous systems. We demonstrate that ISD-SLAM accurately detects LiDAR spoofing attacks, including D-SLAMSpoof, and effectively mitigates the resulting position drift. Our findings expose inherent vulnerabilities in LiDAR-based SLAM and introduce the first practical defense against LiDAR-based SLAM spoofing using only standard onboard sensors, providing critical insights for improving the security and reliability of autonomous systems.

Related papers

• Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications [57.33208520608409]
  This paper presents a systematic study of prompt leaking in large language model (LLM)-based applications.<n>We find that over 80% of deployments leak system prompts under realistic adversarial queries.<n>We propose AREA, a practical defense that re-anchors the model's attention using an optimizable soft prompt.
  arXiv  Detail & Related papers  (2026-06-17T04:20:00Z)
• Prompt-Unknown Promotion Attacks against LLM-based Sequential Recommender Systems [51.504307822017985]
  Large language model-powered sequential recommender systems (LLM-SRSs) have recently demonstrated remarkable performance.<n>This paper investigates the item promotion attack in LLM-SRSs under a more realistic setting where both the system prompt and victim model are unknown to the attacker.
  arXiv  Detail & Related papers  (2026-04-26T10:09:26Z)
• MirrorDrift: Actuated Mirror-Based Attacks on LiDAR SLAM [5.450994180292697]
  LiDAR SLAM provides high-accuracy localization but is fragile to point-cloud corruption because scan matching assumes geometric consistency.<n>Prior physical attacks on LiDAR SLAM largely rely on LiDAR spoofing via external signal injection.<n>We show that specular reflection offers an injection-free alternative and demonstrate an attack, MirrorDrift, that uses an actuated planar mirror to cause ghost points in LiDAR scans.
  arXiv  Detail & Related papers  (2026-03-11T23:03:05Z)
• DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks [87.66245688589977]
  LLM-integrated applications and agents are vulnerable to prompt injection attacks.<n>A detection method aims to determine whether a given input is contaminated by an injected prompt.<n>We propose DataSentinel, a game-theoretic method to detect prompt injection attacks.
  arXiv  Detail & Related papers  (2025-04-15T16:26:21Z)
• SLACK: Attacking LiDAR-based SLAM with Adversarial Point Injections [1.6567468717846674]
  No major work exists that studies learning-based attacks on LiDAR-based SLAM.<n>Our work proposes SLACK, an end-to-end deep generative adversarial model to attack LiDAR scans with several point injections without deteriorating LiDAR quality.
  arXiv  Detail & Related papers  (2025-04-03T23:52:49Z)
• ROLO-SLAM: Rotation-Optimized LiDAR-Only SLAM in Uneven Terrain with Ground Vehicle [49.61982102900982]
  A LiDAR-based SLAM method is presented to improve the accuracy of pose estimations for ground vehicles in rough terrains.<n>A global-scale factor graph is established to aid in the reduction of cumulative errors.<n>The results demonstrate that ROLO-SLAM excels in pose estimation of ground vehicles and outperforms existing state-of-the-art LiDAR SLAM frameworks.
  arXiv  Detail & Related papers  (2025-01-04T02:44:27Z)
• Attention Tracker: Detecting Prompt Injection Attacks in LLMs [62.247841717696765]
  Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks.<n>We introduce the concept of the distraction effect, where specific attention heads shift focus from the original instruction to the injected instruction.<n>We propose Attention Tracker, a training-free detection method that tracks attention patterns on instruction to detect prompt injection attacks.
  arXiv  Detail & Related papers  (2024-11-01T04:05:59Z)
• LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splatting [53.58528891081709]
  We present LiDAR-GS, a real-time, high-fidelity re-simulation of LiDAR scans in public urban road scenes.<n>The method achieves state-of-the-art results in both rendering frame rate and quality on publically available large scene datasets.
  arXiv  Detail & Related papers  (2024-10-07T15:07:56Z)
• ADoPT: LiDAR Spoofing Attack Detection Based on Point-Level Temporal Consistency [11.160041268858773]
  Deep neural networks (DNNs) are increasingly integrated into LiDAR-based perception systems for autonomous vehicles (AVs) We aim to address the challenge of LiDAR spoofing attacks, where attackers inject fake objects into LiDAR data and fool AVs to misinterpret their environment and make erroneous decisions. We propose ADoPT (Anomaly Detection based on Point-level Temporal consistency), which quantitatively measures temporal consistency across consecutive frames and identifies abnormal objects based on the coherency of point clusters. In our evaluation using the nuScenes dataset, our algorithm effectively counters various LiDAR spoofing attacks, achieving a low (
  arXiv  Detail & Related papers  (2023-10-23T02:31:31Z)
• Quantum secured LiDAR with Gaussian modulated coherent states [6.207058145190368]
  LiDAR systems that rely on classical signals are susceptible to intercept-and-recent spoofing attacks. We propose a quantum-secured LiDAR protocol that utilizes Gaussian modulated coherent states for both range determination and spoofing attack detection.
  arXiv  Detail & Related papers  (2023-08-23T14:45:39Z)
• Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasures [24.708895480220733]
  LiDAR-based perception is vulnerable to spoofing attacks, in which adversaries spoof a fake vehicle in front of a victim self-driving car. We perform the first study to explore the general vulnerability of current LiDAR-based perception architectures. We construct the first black-box spoofing attack based on our identified vulnerability, which universally achieves around 80% mean success rates.
  arXiv  Detail & Related papers  (2020-06-30T17:07:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.