Certification of embedded systems based on Machine Learning: A survey
arXiv:2106.07221
Abstract
Advances in machine learning (ML) open the way to innovating functions in the avionic domain, such as navigation/surveillance assistance (e.g. vision-based navigation, obstacle sensing, virtual sensing), speechto-text applications, autonomous flight, predictive maintenance or cockpit assistance. Current certification standards and practices, which were defined and refined decades over decades with classical programming in mind, do not however support this new development paradigm. This article provides an overview of the main challenges raised by the use ML in the demonstration of compliance with regulation requirements, and a survey of literature relevant to these challenges, with particular focus on the issues of robustness and explainability of ML results.
References in corpus (14)
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- Learning Important Features Through Propagating Activation Differences
- ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
- Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
- Understanding Black-box Predictions via Influence Functions
- Sanity Checks for Saliency Maps
- On Evaluating Adversarial Robustness
- Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
- Local Rule-Based Explanations of Black Box Decision Systems
- A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks
- Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
- Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges
- On the Hardness of Robust Classification
- Practical No-box Adversarial Attacks against DNNs