mlsanityData to 14 Oct 2026

Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects

arXiv 2304.08275 ↗First posted 17 Apr 2023cs.CY cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Many sets of ethics principles for responsible AI have been proposed to allay concerns about misuse and abuse of AI/ML systems. The underlying aspects of such sets of principles include privacy, accuracy, fairness, robustness, explainability, and transparency. However, there are potential tensions between these aspects that pose difficulties for AI/ML developers seeking to follow these principles. For example, increasing the accuracy of an AI/ML system may reduce its explainability. As part of the ongoing effort to operationalise the principles into practice, in this work we compile and discuss a catalogue of 10 notable tensions, trade-offs and other interactions between the underlying aspects. We primarily focus on two-sided interactions, drawing on support spread across a diverse literature. This catalogue can be helpful in raising awareness of the possible interactions between aspects of ethics principles, as well as facilitating well-supported judgements by the designers and developers of AI/ML systems.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 36 of its 92 references that are in the map. First posted on arXiv 17 Apr 2023.

Builds on

36 of 92 references.

References · 36

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  5. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  6. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  7. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  9. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  10. 2018Robustness May Be at Odds with Accuracycited by 880
  11. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  12. 2019Federated Machine Learning: Concept and Applicationscited by 412
24 more
  1. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  2. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 237
  3. 2018A comparative study of fairness-enhancing interventions in machine learningcited by 208
  4. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 156
  5. 2018Counterfactual Fairness in Text Classification through Robustnesscited by 151
  6. 2018Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Modelscited by 135
  7. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  8. 2019Fairness in Deep Learning: A Computational Perspectivecited by 123
  9. 2019Artificial Intelligence: the global landscape of ethics guidelinescited by 107
  10. 2017Toward Robustness against Label Noise in Training Deep Discriminative Neural Networkscited by 78
  11. 2018Achieving Fairness through Adversarial Learning: an Application to Recidivism Predictioncited by 77
  12. 2018Differentially Private Fair Learningcited by 76
  13. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  14. 2019Differentially Private Model Publishing for Deep Learningcited by 71
  15. 2018Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Makingcited by 67
  16. 2022Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learningcited by 48
  17. 2020Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracycited by 45
  18. 2017Interpretability via Model Extractioncited by 40
  19. 2017Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developmentscited by 30
  20. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  21. 2021Secure Quantized Training for Deep Learningcited by 15
  22. 2021AI Ethics Principles in Practice: Perspectives of Designers and Developerscited by 12
  23. 2021On the robustness of randomized classifiers to adversarial examplescited by 9
  24. 2022It is not "accuracy vs. explainability" -- we need both for trustworthy AI systemscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 1.

6 papers.

  1. 2025Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Reviewcited by 2
  2. 2024Extreme Value Modelling of Feature Residuals for Anomaly Detection in Dynamic Graphscited by 1
  3. 2025Automated Harmfulness Testing for Code Large Language Modelscited by 0
  4. 2025Reconfiguring Digital Accountability: AI-Powered Innovations and Transnational Governance in a Postnational Accounting Contextcited by 0
  5. 2025Predicting Graph Structure via Adapted Flux Balance Analysiscited by 0
  6. 2026Epistemic Trustworthiness in Generative AI: A Normative Framework for Warranted Reliance in High-Stakes Workflowscited by 0