CP-Guard+: A New Paradigm for Malicious Agent Detection and Defense in Collaborative Perception

Senkang Hu1*, Yihang Tao1*, Zihan Fang1, Guowen Xu2, Yiqin Deng1, Sam Kwong3, Yuguang Fang1
1Department of Computer Science, City University of Hong Kong
2School of Computer Science and Engineering, University of Electronic Science and Technology of China
3Department of Computing and Decision Sciences, Lingnan University

* Equal contribution
Corresponding author: Yuguang Fang

Abstract

Collaborative perception (CP) is a promising method for safe connected and autonomous driving, which enables multiple connected and autonomous vehicles (CAVs) to share sensing information with each other to enhance perception performance. For example, occluded objects can be detected, and the sensing range can be extended. However, compared with single-agent perception, the openness of a CP system makes it more vulnerable to malicious agents and attackers, who can inject malicious information to mislead the perception of an ego CAV, resulting in severe risks for the safety of autonomous driving systems.

To mitigate the vulnerability of CP systems, we first propose a new paradigm for malicious agent detection that effectively identifies malicious agents at the feature level without requiring verification of final perception results, significantly reducing computational overhead. Building on this paradigm, we introduce CP-GuardBench, the first comprehensive dataset provided to train and evaluate various malicious agent detection methods for CP systems. Furthermore, we develop a robust defense method called CP-Guard+, which enhances the margin between the representations of benign and malicious features through a carefully designed mixed contrastive training strategy. Finally, we conduct extensive experiments on both CP-GuardBench and V2X-Sim, and the results demonstrate the superiority of CP-Guard+.

Problem Illustration

Threats in Collaborative Perception
(a) Illustration of the threats of malicious agent in collaborative perception. Malicious CAVs could send intricately crafted adversarial messages to an ego CAV, which will mislead it to generate false positive perception outputs.
Paradigm Comparison
(b) Comparison between the proposed CP-Guard+ with the traditional hypothesize-and-verify malicious agent detection methods. CP-Guard+ directly outputs robust CP results with intermediate feature-level detection, significantly reducing computational overhead.

Our Approach

Key Innovation: Feature-level malicious agent detection paradigm that eliminates the need for final perception result verification, significantly reducing computational overhead.

CP-GuardBench Dataset

The first comprehensive dataset specifically designed for training and evaluating malicious agent detection methods in collaborative perception systems, containing diverse attack scenarios and perturbation levels. This dataset enables systematic evaluation of defense methods across multiple attack types and intensities.

Continuous training process
Figure: Continuous training process for CP-Guard+ with mixed contrastive learning strategy.

Mixed Contrastive Training

A carefully designed training strategy that enhances the margin between benign and malicious feature representations through mixed contrastive learning. This approach enables robust detection of adversarial agents while maintaining computational efficiency.

Feature-Level Detection

Direct identification of malicious agents at the feature level before final perception results are computed, achieving superior detection accuracy with minimal computational overhead compared to traditional hypothesize-and-verify methods.

CP-GuardBench Dataset

Dataset statistics showing attack distributions
Figure: CP-GuardBench dataset statistics showing distribution of attack types and perturbation levels.

Dataset Features

Experimental Results

Key Performance: CP-Guard+ achieves over 98% accuracy across multiple attack types including PGD, BIM, and C&W attacks.

CP-GuardBench Performance

At perturbation budget Δ = 0.25, CP-Guard+ achieves over 98% accuracy for PGD, BIM, and C&W attacks. FGSM and GN attacks show accuracy around 91.64% and 90.95% respectively. With Δ = 0.5, the model maintains an average accuracy of 98.08%.

Attack Type Accuracy (%) TPR (%) FPR (%) F1 Score (%)
PGD (Δ=0.25)98.9299.150.3198.53
BIM (Δ=0.25)98.7698.940.4498.65
C&W (Δ=0.25)98.8399.020.3798.73
FGSM (Δ=0.25)91.6487.324.0490.11
GN (Δ=0.25)90.9585.673.7789.84

Generalization Study

Using leave-one-out evaluation, CP-Guard+ demonstrates strong generalization to unseen attacks with an average accuracy of 98.23% across all attack types.

Performance Comparison on V2X-Sim

On V2X-Sim dataset, CP-Guard+ outperforms MADE and ROBOSAC by significant margins. For Δ=0.25 and 1 malicious agent, CP-Guard+ achieves 71.88% AP@0.5 and 69.92% AP@0.7, outperforming the no-defense case by over 186% and 196% respectively.

Method AP@0.5 (%) AP@0.7 (%) Improvement over No Defense
No Defense25.1323.64-
MADE65.4262.81+160.3% / +165.7%
ROBOSAC58.9156.23+134.4% / +137.9%
CP-Guard+71.8869.92+186.0% / +196.0%

Computational Efficiency

CP-Guard+ achieves 70.36 FPS, representing a 23.74% improvement over MADE and 238.92% improvement over ROBOSAC, demonstrating superior computational efficiency.

FPS performance comparison
Figure: Computational efficiency comparison showing FPS performance across different defense methods.

Additional Visualizations

Effectiveness of DCCLoss and contrastive training
Figure: Ablation study results showing the effectiveness of DCCLoss and mixed contrastive training strategy.
ROC curve analysis
Figure: ROC curve analysis demonstrating the robust detection capabilities of CP-Guard+ across different attack types.