nn-dependability-kit: Engineering Neural Networks for Safety-Critical Autonomous Driving Systems
arXiv:1811.06746
Abstract
Can engineering neural networks be approached in a disciplined way similar to how engineers build software for civil aircraft? We present nn-dependability-kit, an open-source toolbox to support safety engineering of neural networks for autonomous driving systems. The rationale behind nn-dependability-kit is to consider a structured approach (via Goal Structuring Notation) to argue the quality of neural networks. In particular, the tool realizes recent scientific results including (a) novel dependability metrics for indicating sufficient elimination of uncertainties in the product life cycle, (b) formal reasoning engine for ensuring that the generalization does not lead to undesired behaviors, and (c) runtime monitoring for reasoning whether a decision of a neural network in operation is supported by prior similarities in the training data. A proprietary version of nn-dependability-kit has been used to improve the quality of a level-3 autonomous driving component developed by Audi for highway maneuvers.
arXiv commentTool available at https://github.com/dependable-ai/nn-dependability-kit
References in corpus (12)
- End to End Learning for Self-Driving Cars
- DeepXplore: Automated Whitebox Testing of Deep Learning Systems
- Provable defenses against adversarial examples via the convex outer adversarial polytope
- An Empirical Evaluation of Deep Learning on Highway Driving
- Formal Security Analysis of Neural Networks using Symbolic Intervals
- Testing Deep Neural Networks
- A Dual Approach to Scalable Verification of Deep Networks
- Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks
- Towards Verified Artificial Intelligence
- Distance-based Confidence Score for Neural Network Classifiers
- End-to-end Learning of Driving Models from Large-scale Video Datasets
- Concolic Testing for Deep Neural Networks