mlsanityData to 7 Oct 2026

Hazards in Deep Learning Testing: Prevalence, Impact and Recommendations

arXiv 2309.05381 ↗First posted 11 Sep 2023cs.SE cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Much research on Machine Learning testing relies on empirical studies that evaluate and show their potential. However, in this context empirical results are sensitive to a number of parameters that can adversely impact the results of the experiments and potentially lead to wrong conclusions (Type I errors, i.e., incorrectly rejecting the Null Hypothesis). To this end, we survey the related literature and identify 10 commonly adopted empirical evaluation hazards that may significantly impact experimental results. We then perform a sensitivity analysis on 30 influential studies that were published in top-tier SE venues, against our hazard set and demonstrate their criticality. Our findings indicate that all 10 hazards we identify have the potential to invalidate experimental findings, such as those made by the related literature, and should be handled properly. Going a step further, we propose a point set of 10 good empirical practices that has the potential to mitigate the impact of the hazards. We believe our work forms the first step towards raising awareness of the common pitfalls and good practices within the software engineering community and hopefully contribute towards setting particular expectations for empirical research in the field of deep learning testing.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 60 references that are in the map. First posted on arXiv 11 Sep 2023.

Builds on

43 of 60 references.

References · 43

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  7. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  9. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  10. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  11. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  12. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
31 more
  1. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  2. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  3. 2018Robustness May Be at Odds with Accuracycited by 873
  4. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  5. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  6. 2019Adversarial Training for Free!cited by 638
  7. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  8. 2019On Evaluating Adversarial Robustnesscited by 442
  9. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  10. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 307
  11. 2021Improving Robustness using Generated Datacited by 233
  12. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
  13. 2019Machine Learning Testing: Survey, Landscapes and Horizonscited by 213
  14. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  15. 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 181
  16. 2020Torchattacks: A PyTorch Repository for Adversarial Attackscited by 156
  17. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
  18. 2020Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuningcited by 152
  19. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  20. 2018Guiding Deep Learning System Testing using Surprise Adequacycited by 123
  21. 2019Fairness in Deep Learning: A Computational Perspectivecited by 123
  22. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  23. 2020The iWildCam 2020 Competition Datasetcited by 86
  24. 2020Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attackscited by 65
  25. 2019Test Selection for Deep Learning Systemscited by 27
  26. 2020MaxUp: A Simple Way to Improve Generalization of Neural Network Trainingcited by 27
  27. 2021RobOT: Robustness-Oriented Testing for Deep Learning Systemscited by 27
  28. 2022Simple Techniques Work Surprisingly Well for Neural Network Test Prioritization and Active Learning (Replicability Study)cited by 27
  29. 2019Arachne: Search Based Repair of Deep Neural Networkscited by 25
  30. 2019Learning to Sample: an Active Learning Frameworkcited by 11
  31. 2023GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Taskscited by 4

Built on by

Not cited yet.