# PaRoT: A Practical Framework for Robust Deep Neural Network Training

arXiv: https://arxiv.org/abs/2001.02152 · HTML: https://mlsanity.com/paper/2001.02152/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jan 2020.

## Built on by (most cited first, 7 of 7)

- [How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review](https://mlsanity.com/paper/2107.12045/) (2021)
- [The Role of Explainability in Assuring Safety of Machine Learning in Healthcare](https://mlsanity.com/paper/2109.00520/) (2021)
- [PILOT: Efficient Planning by Imitation Learning and Optimisation for Safe Autonomous Driving](https://mlsanity.com/paper/2011.00509/) (2020)
- [Efficient Error Certification for Physics-Informed Neural Networks](https://mlsanity.com/paper/2305.10157/) (2023)
- [Verifiable Goal Recognition for Autonomous Driving with Occlusions](https://mlsanity.com/paper/2206.14163/) (2022)
- [CheckINN: Wide Range Neural Network Verification in Imandra (Extended)](https://mlsanity.com/paper/2207.10562/) (2022)
- [Certifying Ensembles: A General Certification Theory with S-Lipschitzness](https://mlsanity.com/paper/2304.13019/) (2023)

## Abstract (arXiv)

Deep Neural Networks (DNNs) are finding important applications in safety-critical systems such as Autonomous Vehicles (AVs), where perceiving the environment correctly and robustly is necessary for safe operation. Raising unique challenges for assurance due to their black-box nature, DNNs pose a fundamental problem for regulatory acceptance of these types of systems. Robust training --- training to minimize excessive sensitivity to small changes in input --- has emerged as one promising technique to address this challenge. However, existing robust training tools are inconvenient to use or apply to existing codebases and models: they typically only support a small subset of model elements and require users to extensively rewrite the training code. In this paper we introduce a novel framework, PaRoT, developed on the popular TensorFlow platform, that greatly reduces the barrier to entry. Our framework enables robust training to be performed on arbitrary DNNs without any rewrites to the model. We demonstrate that our framework's performance is comparable to prior art, and exemplify its ease of use on off-the-shelf, trained models and its testing capabilities on a real-world industrial application: a traffic light detection network.