.png){kind=icon}
.png){kind=icon}
Return
GCP: Guarded Collaborative Perception With Spatial-Temporal Aware Malicious Agent Detection
.png){kind=icon}
PRE
AI
Y
S
Y
H
H
Y
DOI：10.1109/tdsc.2026.3693684.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Collaborative perception significantly enhances autonomous driving safety by extending each vehicle’s perception range through message sharing among connected and autonomous vehicles. Unfortunately, it is also vulnerable to adversarial message attacks from malicious agents, resulting in severe performance degradation. While existing defenses employ hypothesis-and-verification frameworks to detect malicious agents based on single-shot outliers, they overlook temporal message correlations, which can be circumvented by subtle yet harmful perturbations in model input and output spaces. This paper reveals a novel blind area confusion (BAC) attack that compromises existing single-shot outlier-based detection methods. As a countermeasure, we propose <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GCP</monospace>, a <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>G</u></b>uarded <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>C</u></b>ollaborative <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><u>P</u></b>erception framework based on spatial-temporal aware malicious agent detection, which maintains single-shot spatial consistency through a confidence-scaled spatial concordance loss, while simultaneously examining temporal anomalies by reconstructing historical bird’s eye view motion flows in low-confidence regions. We also employ a joint spatial-temporal Benjamini-Hochberg test to synthesize dual-domain anomaly results for reliable malicious agent detection. Extensive experiments demonstrate <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GCP</monospace>’s superior performance under diverse attack scenarios, achieving up to 34.69% improvements in AP@0.5 compared to the state-of-the-art CP defense strategies under BAC attacks, while maintaining consistent 5-8% improvements under other typical attacks.
Keywords:
Connected and autonomous vehicle (CAV)
collaborative perception
adversarial attack and defense
Journal
IF:
7.5
Papers:
2.4K
Citations:
9.6K
Organization
Cited Papers