CP-FREEZER: Latency Attacks against Vehicular Cooperative Perception
This work addresses a critical threat to the availability of CP systems for autonomous vehicles, revealing a previously unexplored vulnerability in timeliness attacks.
The paper tackles the problem of latency attacks on vehicular cooperative perception (CP) systems, which are safety-critical for autonomous driving, by introducing CP-FREEZER, an attack that injects adversarial perturbations via V2V messages to maximize computation delay. The result shows that CP-FREEZER increases end-to-end CP latency by over 90 times, pushing per-frame processing time beyond 3 seconds with a 100% success rate in real-world tests.
Cooperative perception (CP) enhances situational awareness of connected and autonomous vehicles by exchanging and combining messages from multiple agents. While prior work has explored adversarial integrity attacks that degrade perceptual accuracy, little is known about CP's robustness against attacks on timeliness (or availability), a safety-critical requirement for autonomous driving. In this paper, we present CP-FREEZER, the first latency attack that maximizes the computation delay of CP algorithms by injecting adversarial perturbation via V2V messages. Our attack resolves several unique challenges, including the non-differentiability of point cloud preprocessing, asynchronous knowledge of the victim's input due to transmission delays, and uses a novel loss function that effectively maximizes the execution time of the CP pipeline. Extensive experiments show that CP-FREEZER increases end-to-end CP latency by over $90\times$, pushing per-frame processing time beyond 3 seconds with a 100% success rate on our real-world vehicle testbed. Our findings reveal a critical threat to the availability of CP systems, highlighting the urgent need for robust defenses.