Realistic Adversarial Attacks for Robustness Evaluation of Trajectory Prediction Models via Future State Perturbation
ACM Journal on Autonomous Transportation Systems · 31.12.2026 · 3 (4) · 1-26
DOI: 10.1145/3799894 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Journal on Autonomous Transportation Systems, online erschienen am 16.07.2026. Verfasst von Julian Schumann und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Trajectory prediction is a key element of autonomous vehicle systems, enabling them to anticipate and react to the movements of other road users. Evaluating the robustness of prediction models against adversarial attacks is essential to ensure their reliability in real-world traffic. However, current approaches tend to focus on perturbing the past positions of surrounding agents, which can generate unrealistic scenarios and overlook critical vulnerabilities. In this work, we demonstrate that perturbing not just past but also future states of adversarial agents can uncover previously undetected weaknesses and thereby provide a more rigorous evaluation of model robustness. Our novel approach incorporates dynamic constraints and preserves tactical behaviors, enabling more effective and realistic adversarial attacks. We introduce new performance measures to assess the realism and impact of these adversarial trajectories. Testing our method on two state-of-the-art prediction models across multiple datasets revealed significant increases in prediction errors and collision rates under adversarial conditions. Qualitative analysis further showed that our attacks can expose critical weaknesses, such as the inability of the model to detect potential collisions in what appear to be safe predictions. These results underscore the need for more comprehensive adversarial testing to better evaluate and improve the reliability of trajectory prediction models for autonomous vehicles.
Zitieren
APA
Schumann, J., Hagenus, J., Mathiesen, F., & Zgonnikov, A. (2026). Realistic Adversarial Attacks for Robustness Evaluation of Trajectory Prediction Models via Future State Perturbation. ACM Journal on Autonomous Transportation Systems, 3(4), 1-26. https://doi.org/10.1145/3799894
Vancouver
Schumann J, Hagenus J, Mathiesen F, Zgonnikov A. Realistic Adversarial Attacks for Robustness Evaluation of Trajectory Prediction Models via Future State Perturbation. ACM Journal on Autonomous Transportation Systems. 2026;3(4):1-26. doi:10.1145/3799894
BibTeX
@article{Schumann2026,
author = {Schumann, Julian and Hagenus, Jeroen and Mathiesen, Frederik and Zgonnikov, Arkady},
title = {Realistic Adversarial Attacks for Robustness Evaluation of Trajectory Prediction Models via Future State Perturbation},
journal = {ACM Journal on Autonomous Transportation Systems},
year = {2026},
volume = {3},
number = {4},
pages = {1--26},
doi = {10.1145/3799894}
}
EUVIMED