Saved in:
Bibliographic Details
Main Authors: Zhang, Qingzhao, Zhang, Runting, Mao, Z. Morley
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.01301
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909010020532224
author Zhang, Qingzhao
Zhang, Runting
Mao, Z. Morley
author_facet Zhang, Qingzhao
Zhang, Runting
Mao, Z. Morley
contents Collaborative perception allows connected and autonomous vehicles (CAVs) to improve perception by sharing sensory data, but it also introduces security risks from manipulated inputs. Prior work shows that attackers can spoof or remove objects by fabricating shared data, yet the practicality of such attacks in real-world driving remains unclear. Existing attacks are often detectable or evaluated in manually constructed scenarios, leaving open whether they can induce safety-critical outcomes in dynamic environments. To bridge this gap, we present a stealthy, scenario-realistic data fabrication attack that induces unsafe driving behaviors through end-to-end system effects. Instead of creating large, easily detectable anomalies, our attack subtly manipulates the poses of existing objects in shared perception results, keeping perturbations below detection thresholds. These small errors are then propagated through downstream modules, including object tracking and trajectory prediction, leading to significant deviations in predicted behaviors and ultimately unsafe driving decisions. We further design an online, scenario-aware attack framework that adapts to dynamic traffic conditions and optimizes attack strategies at runtime. Experiments on OPV2V and V2X-Real demonstrate that the attack achieves over 90% success in inducing detection errors and triggers safety-critical behaviors, such as unnecessary hard braking, in up to 50% of scenarios, while largely evading state-of-the-art defenses. We also propose a mitigation that focuses on detecting anomalies in localized, safety-critical regions, achieving an 80% detection rate on the small pose perturbation compared to 11% for the best existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2605_01301
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Stealthy Data Fabrication to Unsafe Driving: Realistic Scenario Attacks on Collaborative Perception
Zhang, Qingzhao
Zhang, Runting
Mao, Z. Morley
Cryptography and Security
Collaborative perception allows connected and autonomous vehicles (CAVs) to improve perception by sharing sensory data, but it also introduces security risks from manipulated inputs. Prior work shows that attackers can spoof or remove objects by fabricating shared data, yet the practicality of such attacks in real-world driving remains unclear. Existing attacks are often detectable or evaluated in manually constructed scenarios, leaving open whether they can induce safety-critical outcomes in dynamic environments. To bridge this gap, we present a stealthy, scenario-realistic data fabrication attack that induces unsafe driving behaviors through end-to-end system effects. Instead of creating large, easily detectable anomalies, our attack subtly manipulates the poses of existing objects in shared perception results, keeping perturbations below detection thresholds. These small errors are then propagated through downstream modules, including object tracking and trajectory prediction, leading to significant deviations in predicted behaviors and ultimately unsafe driving decisions. We further design an online, scenario-aware attack framework that adapts to dynamic traffic conditions and optimizes attack strategies at runtime. Experiments on OPV2V and V2X-Real demonstrate that the attack achieves over 90% success in inducing detection errors and triggers safety-critical behaviors, such as unnecessary hard braking, in up to 50% of scenarios, while largely evading state-of-the-art defenses. We also propose a mitigation that focuses on detecting anomalies in localized, safety-critical regions, achieving an 80% detection rate on the small pose perturbation compared to 11% for the best existing methods.
title From Stealthy Data Fabrication to Unsafe Driving: Realistic Scenario Attacks on Collaborative Perception
topic Cryptography and Security
url https://arxiv.org/abs/2605.01301