mlsanityData to 7 Oct 2026

Towards certifiable AI in aviation: landscape, challenges, and opportunities

arXiv 2409.08666 ↗First posted 13 Sep 2024cs.LG cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Artificial Intelligence (AI) methods are powerful tools for various domains, including critical fields such as avionics, where certification is required to achieve and maintain an acceptable level of safety. General solutions for safety-critical systems must address three main questions: Is it suitable? What drives the system's decisions? Is it robust to errors/attacks? This is more complex in AI than in traditional methods. In this context, this paper presents a comprehensive mind map of formal AI certification in avionics. It highlights the challenges of certifying AI development with an example to emphasize the need for qualification beyond performance metrics.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 75 of its 174 references that are in the map. First posted on arXiv 13 Sep 2024.

Builds on

75 of 174 references.

References · 75

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  5. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  6. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  7. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  8. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  9. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  10. 2019Graph Transformer Networkscited by 520
  11. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  12. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 503
38 more
  1. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  2. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  3. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  4. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  5. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 312
  6. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 307
  7. 2020AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradientscited by 282
  8. 2018DropBlock: A regularization method for convolutional networkscited by 261
  9. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  10. 2018Deep Learning in Spiking Neural Networkscited by 258
  11. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 249
  12. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 224
  13. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  14. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  15. 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisonscited by 169
  16. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  17. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
  18. 2018DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systemscited by 144
  19. 2020REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasetscited by 136
  20. 2018NetGAN: Generating Graphs via Random Walkscited by 129
  21. 2022Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modelingcited by 126
  22. 2018Guiding Deep Learning System Testing using Surprise Adequacycited by 123
  23. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  24. 2023A Definition of Continual Reinforcement Learningcited by 98
  25. 2017Regularization for Deep Learning: A Taxonomycited by 91
  26. 2020Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantificationcited by 77
  27. 2021A Survey on Interpretable Reinforcement Learningcited by 70
  28. 2018DeepMutation: Mutation Testing of Deep Learning Systemscited by 66
  29. 2021Uncertainty Toolbox: an Open-Source Library for Assessing, Visualizing, and Improving Uncertainty Quantificationcited by 57
  30. 2023Time Series Contrastive Learning with Information-Aware Augmentationscited by 52
  31. 2020Uncertainty-Aware Deep Classifiers using Generative Modelscited by 41
  32. 2024Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Makingcited by 38
  33. 2020Trust in AutoML: Exploring Information Needs for Establishing Trust in Automated Machine Learning Systemscited by 36
  34. 2023Improving Human-AI Collaboration With Descriptions of AI Behaviorcited by 35
  35. 2018YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computerscited by 34
  36. 2022NeuralUQ: A comprehensive library for uncertainty quantification in neural differential equations and operatorscited by 33
  37. 2023PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learningcited by 31
  38. 2024AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Searchcited by 25

50 most cited of 75 All 75 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024Enhancing Interpretability Through Loss-Defined Classification Objective in Structured Latent Spacescited by 2
  2. 2026Defining Operational Conditions for Safety-Critical AI-Based Systems from Datacited by 1