Still Camouflage, Moving Illusion: View-Induced Trajectory Manipulation in Autonomous Driving

TL;DR

This paper introduces a novel passive camouflage attack that exploits view-dependent appearance changes to induce false trajectories in autonomous vehicles, causing unnecessary braking.

Contribution

It presents a new attack paradigm leveraging natural view-dependent appearance evolution, avoiding complex multi-view optimization required by prior methods.

Findings

Achieved up to 87.5% success rate in inducing hard braking.

Demonstrated robustness across various backgrounds, speeds, and perception models.

Effective with a simple, passive camouflage on parked vehicles.

Abstract

Existing physical adversarial attacks on vision-based autonomous driving induce time-evolving perception errors, including biased object tracking or trajectory prediction, through (i) sophisticated physical patch inducing detection box drift when entering the view distance, or (ii) dynamically changing patches that cause different perception errors at different time. In both cases, viewing-angle variation is treated as a challenge, requiring adversarial patches to remain effective across frames under varying views, leading to complex multi-view optimization. In contrast, we show that viewing-angle variation itself can be turned into an attack tool. We design a new attack paradigm where a static, passive adversarial camouflage is mounted on a vehicle whose view-dependent appearance naturally evolves with relative motion, inducing consistent feature drift across frames. This causes the system to infer a physically plausible but incorrect trajectory, such as a false cut-in, which propagates to downstream decision-making and triggers unnecessary braking. Unlike prior approaches that require multi-view robustness or active intervention, our attack emerges from normal driving dynamics and is easy to deploy: a parked vehicle with a natural camouflage can induce hard braking in passing autonomous vehicles. We demonstrate the novel attack on nuScenes dataset, showing the effectiveness with an end-to-end success rate of up to 87.5%, measured by hard-braking events, and robustness across different scene backgrounds, victim vehicle speeds, and perception models.