# AutoJoin: Efficient Adversarial Training against Gradient-Free Perturbations for Robust Maneuvering via Denoising Autoencoder and Joint Learning

arXiv: https://arxiv.org/abs/2205.10933 · HTML: https://mlsanity.com/paper/2205.10933/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 22 May 2022.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser](https://mlsanity.com/paper/1712.02976/) (2017)
- [Feature Denoising for Improving Adversarial Robustness](https://mlsanity.com/paper/1812.03411/) (2018)
- [A2D2: Audi Autonomous Driving Dataset](https://mlsanity.com/paper/2004.06320/) (2020)
- [Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning](https://mlsanity.com/paper/2003.12862/) (2020)
- [Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds](https://mlsanity.com/paper/2007.08488/) (2020)
- [Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning](https://mlsanity.com/paper/1811.02307/) (2018)
- [AugMax: Adversarial Composition of Random Augmentations for Robust Training](https://mlsanity.com/paper/2110.13771/) (2021)
- [Temporal Recurrent Networks for Online Action Detection](https://mlsanity.com/paper/1811.07391/) (2018)
- [Enhancing Robustness of Machine Learning Systems via Data Transformations](https://mlsanity.com/paper/1704.02654/) (2017)
- [DriveGuard: Robustification of Automated Driving Systems with Deep Spatio-Temporal Convolutional Autoencoder](https://mlsanity.com/paper/2111.03480/) (2021)

## Built on by (most cited first, 4 of 4)

- [Can ChatGPT Enable ITS? The Case of Mixed Traffic Control via Reinforcement Learning](https://mlsanity.com/paper/2306.08094/) (2023)
- [CARL: Congestion-Aware Reinforcement Learning for Imitation-based Perturbations in Mixed Traffic Control](https://mlsanity.com/paper/2404.00796/) (2024)
- [Towards Increasing the Robustness of Predictive Steering-Control Autonomous Navigation Systems Against Dash Cam Image Angle Perturbations Due to Pothole Encounters](https://mlsanity.com/paper/2310.03959/) (2023)
- [Analyzing Behaviors of Mixed Traffic via Reinforcement Learning at Unsignalized Intersections](https://mlsanity.com/paper/2312.05325/) (2023)

## Abstract (arXiv)

With the growing use of machine learning algorithms and ubiquitous sensors, many `perception-to-control' systems are being developed and deployed. To ensure their trustworthiness, improving their robustness through adversarial training is one potential approach. We propose a gradient-free adversarial training technique, named AutoJoin, to effectively and efficiently produce robust models for image-based maneuvering. Compared to other state-of-the-art methods with testing on over 5M images, AutoJoin achieves significant performance increases up to the 40% range against perturbations while improving on clean performance up to 300%. AutoJoin is also highly efficient, saving up to 86% time per training epoch and 90% training data over other state-of-the-art techniques. The core idea of AutoJoin is to use a decoder attachment to the original regression model creating a denoising autoencoder within the architecture. This architecture allows the tasks `maneuvering' and `denoising sensor input' to be jointly learnt and reinforce each other's performance.