# Evaluating randomized smoothing as a defense against adversarial attacks in trajectory prediction

arXiv: https://arxiv.org/abs/2603.10821 · HTML: https://mlsanity.com/paper/2603.10821/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Certified Robustness to Adversarial Examples with Differential Privacy](https://mlsanity.com/paper/1802.03471/) (2018)
- [Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers](https://mlsanity.com/paper/1906.04584/) (2019)
- [Wayformer: Motion Forecasting via Simple & Efficient Attention Networks](https://mlsanity.com/paper/2207.05844/) (2022)
- [Certified Adversarial Robustness with Additive Noise](https://mlsanity.com/paper/1809.03113/) (2018)
- [Towards Robust Neural Networks via Random Self-ensemble](https://mlsanity.com/paper/1712.00673/) (2017)
- [MotionLM: Multi-Agent Motion Forecasting as Language Modeling](https://mlsanity.com/paper/2309.16534/) (2023)
- [Randomized Smoothing of All Shapes and Sizes](https://mlsanity.com/paper/2002.08118/) (2020)
- [On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles](https://mlsanity.com/paper/2201.05057/) (2022)
- [The Waymo Open Sim Agents Challenge](https://mlsanity.com/paper/2305.12032/) (2023)
- [AdvDO: Realistic Adversarial Attacks for Trajectory Prediction](https://mlsanity.com/paper/2209.08744/) (2022)
- [Detection as Regression: Certified Object Detection by Median Smoothing](https://mlsanity.com/paper/2007.03730/) (2020)
- [FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphs](https://mlsanity.com/paper/2211.16197/) (2022)
- [ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation](https://mlsanity.com/paper/2307.14187/) (2023)
- [SingularTrajectory: Universal Trajectory Predictor Using Diffusion Model](https://mlsanity.com/paper/2403.18452/) (2024)
- [Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attacks](https://mlsanity.com/paper/1910.10783/) (2019)
- [Robust Trajectory Prediction against Adversarial Attacks](https://mlsanity.com/paper/2208.00094/) (2022)
- [Trajectory Prediction Meets Large Language Models: A Survey](https://mlsanity.com/paper/2506.03408/) (2025)
- [Sequential Randomized Smoothing for Adversarially Robust Speech Recognition](https://mlsanity.com/paper/2112.03000/) (2021)
- [On the Robustness of Bayesian Neural Networks to Adversarial Attacks](https://mlsanity.com/paper/2207.06154/) (2022)
- [Benchmark for Models Predicting Human Behavior in Gap Acceptance Scenarios](https://mlsanity.com/paper/2211.05455/) (2022)
- [TrajFlow: Learning Distributions over Trajectories for Human Behavior Prediction](https://mlsanity.com/paper/2304.05166/) (2023)
- [RS-Reg: Probabilistic and Robust Certified Regression Through Randomized Smoothing](https://mlsanity.com/paper/2405.08892/) (2024)
- [Realistic Adversarial Attacks for Robustness Evaluation of Trajectory Prediction Models via Future State Perturbation](https://mlsanity.com/paper/2505.06134/) (2025)
- [STEP: Structured Training and Evaluation Platform for benchmarking trajectory prediction models](https://mlsanity.com/paper/2509.14801/) (2025)

## Built on by (most cited first, 1 of 1)

- [Clustered Randomized Smoothing for Stochastic Prediction Functions](https://mlsanity.com/paper/2608.12037/) (2026)

## Abstract (arXiv)

Accurate and robust trajectory prediction is essential for safe and efficient autonomous driving, yet recent work has shown that even state-of-the-art prediction models are highly vulnerable to inputs being mildly perturbed by adversarial attacks. Although model vulnerabilities to such attacks have been studied, work on effective countermeasures remains limited. In this work, we develop and evaluate a new defense mechanism for trajectory prediction models based on randomized smoothing -- an approach previously applied successfully in other domains. We evaluate its ability to improve model robustness through a series of experiments that test different strategies of randomized smoothing. We show that our approach can consistently improve prediction robustness of multiple base trajectory prediction models in various datasets without compromising accuracy in non-adversarial settings. Our results demonstrate that randomized smoothing offers a simple and computationally inexpensive technique for mitigating adversarial attacks in trajectory prediction.