White Paper Machine Learning in Certified Systems

Abstract

Machine Learning (ML) seems to be one of the most promising solution to automate partially or completely some of the complex tasks currently realized by humans, such as driving vehicles, recognizing voice, etc. It is also an opportunity to implement and embed new capabilities out of the reach of classical implementation techniques. However, ML techniques introduce new potential risks. Therefore, they have only been applied in systems where their benefits are considered worth the increase of risk. In practice, ML techniques raise multiple challenges that could prevent their use in systems submitted to certification constraints. But what are the actual challenges? Can they be overcome by selecting appropriate ML techniques, or by adopting new engineering or certification practices? These are some of the questions addressed by the ML Certification 3 Workgroup (WG) set-up by the Institut de Recherche Technologique Saint Exupéry de Toulouse (IRT), as part of the DEEL Project.

113 pages, White paper

References in corpus (17)

• Auto-Encoding Variational Bayes
• Intriguing properties of neural networks
• NICE: Non-linear Independent Components Estimation
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• Density estimation using Real NVP
• Adversarial Attacks and Defences: A Survey
• On the (Statistical) Detection of Adversarial Examples
• Robustness May Be at Odds with Accuracy
• Simple Black-Box Adversarial Perturbations for Deep Networks
• Causality for Machine Learning
• DeepFool: a simple and accurate method to fool deep neural networks
• Towards Verified Artificial Intelligence
• Output Range Analysis for Deep Neural Networks
• Conformalized Quantile Regression
• Adversarial Explanations for Understanding Image Classification Decisions and Improved Neural Network Robustness
• How to Incorporate Monotonicity in Deep Networks While Preserving Flexibility?
• Controlling Over-generalization and its Effect on Adversarial Examples Generation and Detection

Cited by in corpus (3)

• Toward Certification of Machine-Learning Systems for Low Criticality Airborne Applications
• Deep Anti-Regularized Ensembles provide reliable out-of-distribution uncertainty quantification
• Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain