# Poisoning Attacks on Federated Learning for Autonomous Driving

arXiv: https://arxiv.org/abs/2405.01073 · HTML: https://mlsanity.com/paper/2405.01073/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 2 May 2024.

## Builds on (most cited first, 21 of 21)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning](https://mlsanity.com/paper/1911.11815/) (2019)
- [FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping](https://mlsanity.com/paper/2012.13995/) (2020)
- [The Hidden Vulnerability of Distributed Learning in Byzantium](https://mlsanity.com/paper/1802.07927/) (2018)
- [A Little Is Enough: Circumventing Defenses For Distributed Learning](https://mlsanity.com/paper/1902.06156/) (2019)
- [Data Poisoning Attacks Against Federated Learning Systems](https://mlsanity.com/paper/2007.08432/) (2020)
- [Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization](https://mlsanity.com/paper/1708.08689/) (2017)
- [Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning](https://mlsanity.com/paper/2108.10241/) (2021)
- [Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving](https://mlsanity.com/paper/2305.02008/) (2023)
- [Data Poisoning Attacks on Federated Machine Learning](https://mlsanity.com/paper/2004.10020/) (2020)
- [Deep Federated Learning for Autonomous Driving](https://mlsanity.com/paper/2110.05754/) (2021)
- [Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systems](https://mlsanity.com/paper/2101.03367/) (2021)
- [Universal Multi-Party Poisoning Attacks](https://mlsanity.com/paper/1809.03474/) (2018)
- [FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregation](https://mlsanity.com/paper/2305.05506/) (2023)
- [Dynamic backdoor attacks against federated learning](https://mlsanity.com/paper/2011.07429/) (2020)
- [Backdoor Attack and Defense for Deep Regression](https://mlsanity.com/paper/2109.02381/) (2021)
- [Turn Signal Prediction: A Federated Learning Case Study](https://mlsanity.com/paper/2012.12401/) (2020)

## Abstract (arXiv)

Federated Learning (FL) is a decentralized learning paradigm, enabling parties to collaboratively train models while keeping their data confidential. Within autonomous driving, it brings the potential of reducing data storage costs, reducing bandwidth requirements, and to accelerate the learning. FL is, however, susceptible to poisoning attacks. In this paper, we introduce two novel poisoning attacks on FL tailored to regression tasks within autonomous driving: FLStealth and Off-Track Attack (OTA). FLStealth, an untargeted attack, aims at providing model updates that deteriorate the global model performance while appearing benign. OTA, on the other hand, is a targeted attack with the objective to change the global model's behavior when exposed to a certain trigger. We demonstrate the effectiveness of our attacks by conducting comprehensive experiments pertaining to the task of vehicle trajectory prediction. In particular, we show that, among five different untargeted attacks, FLStealth is the most successful at bypassing the considered defenses employed by the server. For OTA, we demonstrate the inability of common defense strategies to mitigate the attack, highlighting the critical need for new defensive mechanisms against targeted attacks within FL for autonomous driving.