mlsanityData to 7 Oct 2026

Certification of embedded systems based on Machine Learning: A survey

arXiv 2106.07221 ↗First posted 14 Jun 2021cs.AI stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 42 of its 69 references that are in the map. First posted on arXiv 14 Jun 2021.

Builds on

42 of 69 references.

References · 42

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  8. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  10. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  11. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  12. 2016Adversarial examples in the physical worldcited by 1,762
30 more
  1. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  2. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  3. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  4. 2018Sanity Checks for Saliency Mapscited by 1,149
  5. 2016Adversarial Machine Learning at Scalecited by 934
  6. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  7. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  8. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  9. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  10. 2019On Evaluating Adversarial Robustnesscited by 442
  11. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  12. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
  13. 2016Safety Verification of Deep Neural Networkscited by 262
  14. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  15. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 203
  16. 2018Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networkscited by 193
  17. 2018Formal Security Analysis of Neural Networks using Symbolic Intervalscited by 185
  18. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 181
  19. 2018Local Rule-Based Explanations of Black Box Decision Systemscited by 165
  20. 2016Generating Visual Explanationscited by 156
  21. 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 139
  22. 2019A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networkscited by 124
  23. 2019Adversarial Examples Are a Natural Consequence of Test Error in Noisecited by 114
  24. 2020Explaining the Explainer: A First Theoretical Analysis of LIMEcited by 89
  25. 2017Efficient Defenses Against Adversarial Attackscited by 53
  26. 2020Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodologycited by 41
  27. 2019Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challengescited by 39
  28. 2020Practical No-box Adversarial Attacks against DNNscited by 32
  29. 2019On the Hardness of Robust Classificationcited by 23
  30. 2020Ensuring Dataset Quality for Machine Learning Certificationcited by 7

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 2; 2023: 1.

6 papers.

  1. 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Reviewcited by 36
  2. 2021RoMA: a Method for Neural Network Robustness Measurement and Assessmentcited by 10
  3. 2022On the Robustness of Explanations of Deep Neural Network Models: A Surveycited by 5
  4. 2021Agility in Software 2.0 -- Notebook Interfaces and MLOps with Buttresses and Rebarscited by 4
  5. 2022Exploring ML testing in practice -- Lessons learned from an interactive rapid review with Axis Communicationscited by 3
  6. 2023Rethinking Certification for Trustworthy Machine Learning-Based Applicationscited by 2