# Systematic Testing of Convolutional Neural Networks for Autonomous Driving

arXiv: https://arxiv.org/abs/1708.03309 · HTML: https://mlsanity.com/paper/1708.03309/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2017.

## Built on by (most cited first, 5 of 5)

- [Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead](https://mlsanity.com/paper/2101.02559/) (2021)
- [How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review](https://mlsanity.com/paper/2107.12045/) (2021)
- [Can Offline Testing of Deep Neural Networks Replace Their Online Testing?](https://mlsanity.com/paper/2101.11118/) (2021)
- [Monitoring of Perception Systems: Deterministic, Probabilistic, and Learning-based Fault Detection and Identification](https://mlsanity.com/paper/2205.10906/) (2022)
- [Discovering Closed-Loop Failures of Vision-Based Controllers via Reachability Analysis](https://mlsanity.com/paper/2211.02736/) (2022)

## Abstract (arXiv)

We present a framework to systematically analyze convolutional neural networks (CNNs) used in classification of cars in autonomous vehicles. Our analysis procedure comprises an image generator that produces synthetic pictures by sampling in a lower dimension image modification subspace and a suite of visualization tools. The image generator produces images which can be used to test the CNN and hence expose its vulnerabilities. The presented framework can be used to extract insights of the CNN classifier, compare across classification models, or generate training and validation datasets.