mlsanityData to 14 Oct 2026

Trustworthy AI Must Account for Interactions

arXiv 2504.07170 ↗First posted 9 Apr 2025cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Trustworthy AI encompasses many aspirational aspects for aligning AI systems with human values, including fairness, privacy, robustness, explainability, and uncertainty quantification. The ultimate goal of Trustworthy AI research is to achieve all aspects simultaneously. However, efforts to enhance one aspect often introduce unintended trade-offs that negatively impact others. In this position paper, we review notable approaches to five aspects and systematically consider every pair, detailing the negative interactions that can arise. For example, applying differential privacy to model training can amplify biases, undermining fairness. Drawing on these findings, we take the position that current research practices of improving one or two aspects in isolation are insufficient. Instead, research on Trustworthy AI must account for interactions between aspects and adopt a holistic view across all relevant axes at once. We offer recommendations for how researchers can work towards integrated trust, and provide guidance for practitioners to manage interactions today.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 73 of its 106 references that are in the map. First posted on arXiv 9 Apr 2025.

Builds on

73 of 106 references.

References · 73

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  5. 2017On Calibration of Modern Neural Networkscited by 4,960
  6. 2016Deep Learning with Differential Privacycited by 2,728
  7. 2016Concrete Problems in AI Safetycited by 1,642
  8. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  9. 2018Robustness May Be at Odds with Accuracycited by 880
  10. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
  11. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  12. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 571
38 more
  1. 2020Artificial Intelligence, Values and Alignmentcited by 448
  2. 2017Interpretation of Neural Networks is Fragilecited by 444
  3. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 443
  4. 2020Classification with Valid and Adaptive Coveragecited by 396
  5. 2021Revisiting the Calibration of Modern Neural Networkscited by 390
  6. 2020Fairness in Machine Learning: A Surveycited by 370
  7. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 366
  8. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 322
  9. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  10. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  11. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 248
  12. 2020Differentially Private Learning Needs Better Features (or Much More Data)cited by 235
  13. 2021Trustworthy AI: From Principles to Practicescited by 207
  14. 2019R'enyi Differential Privacy of the Sampled Gaussian Mechanismcited by 204
  15. 2023Conformal Prediction With Conditional Guaranteescited by 152
  16. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 141
  17. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  18. 2022The Privacy Onion Effect: Memorization is Relativecited by 136
  19. 2020Reliable Post hoc Explanations: Modeling Uncertainty in Explainabilitycited by 125
  20. 2019"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanationscited by 111
  21. 2023Class-Conditional Conformal Prediction with Many Classescited by 109
  22. 2020Getting a CLUE: A Method for Explaining Uncertainty Estimatescited by 92
  23. 2020On the Privacy Risks of Algorithmic Fairnesscited by 82
  24. 2019Interpreting Adversarially Trained Convolutional Neural Networkscited by 75
  25. 2020Fairness Through Robustness: Investigating Robustness Disparity in Deep Learningcited by 56
  26. 2023Conformal Prediction for Deep Classifier via Label Rankingcited by 53
  27. 2022Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learningcited by 48
  28. 2020Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracycited by 45
  29. 2022The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanationscited by 41
  30. 2021Explainable Artificial Intelligence Approaches: A Surveycited by 40
  31. 2022Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanationscited by 40
  32. 2020On Adversarial Bias and the Robustness of Fair Machine Learningcited by 36
  33. 2021On the Convergence and Calibration of Deep Learning with Differential Privacycited by 36
  34. 2019Disparate Vulnerability to Membership Inference Attackscited by 35
  35. 2021Decision Making with Differential Privacy under a Fairness Lenscited by 32
  36. 2022Disparate Impact in Differential Privacy from Gradient Misalignmentcited by 31
  37. 2022One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacycited by 27
  38. 2023Designing Decision Support Systems Using Counterfactual Prediction Setscited by 26

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Beyond Procedure: Substantive Fairness in Conformal Predictioncited by 2
  2. 2026TabPATE: Differentially Private Tabular In-Context Learning Without Public Datacited by 0
  3. 2026Training Fair Tabular Foundation Modelscited by 0
  4. 2026Quantum-Inspired Modeling of Driving Behaviorcited by 0
  5. 2026Unifying Conformal Language Tasks with In-Context Ensemblescited by 0