mlsanityData to 7 Oct 2026

A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities

arXiv 2210.08906 ↗First posted 17 Oct 2022cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness remains elusive and constitutes a key issue that impedes large-scale adoption. Robustness has been studied in many domains of AI, yet with different interpretations across domains and contexts. In this work, we systematically survey the recent progress to provide a reconciled terminology of concepts around AI robustness. We introduce three taxonomies to organize and describe the literature both from a fundamental and applied point of view: 1) robustness by methods and approaches in different phases of the machine learning pipeline; 2) robustness for specific model architectures, tasks, and systems; and in addition, 3) robustness assessment methodologies and insights, particularly the trade-offs with other trustworthiness properties. Finally, we identify and discuss research gaps and opportunities and give an outlook on the field. We highlight the central role of humans in evaluating and enhancing AI robustness, considering the necessary knowledge humans can provide, and discuss the need for better understanding practices and developing supportive tools in the future.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 243 of its 399 references that are in the map. First posted on arXiv 17 Oct 2022.

Builds on

243 of 399 references.

References · 243

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  9. 2020Learning to summarize from human feedbackcited by 2,562
  10. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  11. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  12. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
38 more
  1. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  2. 2018Datasheets for Datasetscited by 1,371
  3. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  4. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  5. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  6. 2018Model Cards for Model Reportingcited by 1,068
  7. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  8. 2018Robustness May Be at Odds with Accuracycited by 873
  9. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  10. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  11. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
  12. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  13. 2017Exploring Generalization in Deep Learningcited by 595
  14. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  15. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 452
  16. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 443
  17. 2019On Evaluating Adversarial Robustnesscited by 442
  18. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
  19. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  20. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  21. 2021Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarkscited by 388
  22. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
  23. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  24. 2018On the Robustness of Interpretability Methodscited by 310
  25. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  26. 2019Variational Adversarial Active Learningcited by 284
  27. 2019Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoningcited by 281
  28. 2018Improving fairness in machine learning systems: What do industry practitioners need?cited by 262
  29. 2020Questioning the AI: Informing Design Practices for Explainable AI User Experiencescited by 251
  30. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
  31. 2017On Detecting Adversarial Perturbationscited by 232
  32. 2019Human uncertainty makes classification more robustcited by 231
  33. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
  34. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  35. 2019Machine Learning Testing: Survey, Landscapes and Horizonscited by 213
  36. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 212
  37. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 194
  38. 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 181

50 most cited of 243 All 243 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 4.

8 papers.

  1. 2025Robustness and Cybersecurity in the EU Artificial Intelligence Actcited by 10
  2. 2024Sonar-based Deep Learning in Underwater Robotics: Overview, Robustness and Challengescited by 5
  3. 2025Realistic Adversarial Attacks for Robustness Evaluation of Trajectory Prediction Models via Future State Perturbationcited by 3
  4. 2025Fire360: A Benchmark for Robust Perception and Episodic Memory in Degraded 360-Degree Firefighting Videoscited by 2
  5. 2024Complexity Matters: Effective Dimensionality as a Measure for Adversarial Robustnesscited by 1
  6. 2024Assistive AI for Augmenting Human Decision-makingcited by 0
  7. 2024Which PPML Would a User Choose? A Structured Decision Support Framework for Developers to Rank PPML Techniques Based on User Acceptance Criteriacited by 0
  8. 2025SPATA: Systematic Pattern Analysis for Detailed and Transparent Data Cardscited by 0