mlsanityData to 7 Oct 2026

Trustworthy AI: From Principles to Practices

arXiv 2110.01167 ↗First posted 4 Oct 2021cs.AI cs.LGcited by 206

Not on the map. Why?

Abstract (arXiv)

The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, many current AI systems are found vulnerable to imperceptible attacks, biased against underrepresented groups, lacking in user privacy protection. These shortcomings degrade user experience and erode people's trust in all AI systems. In this review, we provide AI practitioners with a comprehensive guide for building trustworthy AI systems. We first introduce the theoretical framework of important aspects of AI trustworthiness, including robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, and accountability. To unify currently available but fragmented approaches toward trustworthy AI, we organize them in a systematic approach that considers the entire lifecycle of AI systems, ranging from data acquisition to model development, to system development and deployment, finally to continuous monitoring and governance. In this framework, we offer concrete action items for practitioners and societal stakeholders (e.g., researchers, engineers, and regulators) to improve AI trustworthiness. Finally, we identify key opportunities and challenges for the future development of trustworthy AI systems, where we identify the need for a paradigm shift toward comprehensively trustworthy AI systems.

Key facts. Cited by 206 papers in the map (data through 7 Oct 2026). Builds on 235 of its 503 references that are in the map. First posted on arXiv 4 Oct 2021.

Builds on

235 of 503 references.

References · 235

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  7. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  8. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  9. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  10. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  11. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  12. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
38 more
  1. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  8. 2016Deep Learning with Differential Privacycited by 2,682
  9. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  10. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  11. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  12. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  13. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  14. 2020Extracting Training Data from Large Language Modelscited by 2,144
  15. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  16. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  17. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  18. 2016Adversarial examples in the physical worldcited by 1,762
  19. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  20. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  21. 2016Concrete Problems in AI Safetycited by 1,582
  22. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  23. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  24. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  25. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  26. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  27. 2018Datasheets for Datasetscited by 1,371
  28. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  29. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  30. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  31. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  32. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  33. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  34. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  35. 2018Model Cards for Model Reportingcited by 1,068
  36. 2019Deep Leakage from Gradientscited by 1,004
  37. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  38. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970

50 most cited of 235 All 235 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 36; 2024: 68; 2025: 58; 2026: 38.

206 papers.

Sort:

By area:

  1. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
  2. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  3. 2023A Review of Uncertainty Estimation and its Application in Medical Imagingcited by 59
  4. 2023Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generatorscited by 56
  5. 2024On Large Language Models' Hallucination with Regard to Known Factscited by 43
  6. 2024Are large language models superhuman chemists?cited by 34
  7. 2023Domain Generalization in Computational Pathology: Survey and Guidelinescited by 29
  8. 2025Language Models Fail to Introspect About Their Knowledge of Languagecited by 28
  9. 2023Aligning Language Models with Human Preferences via a Bayesian Approachcited by 27
  10. 2024MM-SAP: A Comprehensive Benchmark for Assessing Self-Awareness of Multimodal Large Language Models in Perceptioncited by 21
  11. 2021Physics-enhanced deep surrogates for partial differential equationscited by 18
  12. 2023Towards Explainable Evaluation Metrics for Machine Translationcited by 15
38 more
  1. 2024The METRIC-framework for assessing data quality for trustworthy AI in medicine: a systematic reviewcited by 13
  2. 2025Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Surveycited by 13
  3. 2023Optimizing Privacy, Utility and Efficiency in Constrained Multi-Objective Federated Learningcited by 12
  4. 2024Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decodingcited by 12
  5. 2024Establishing and Evaluating Trustworthy AI: Overview and Research Challengescited by 12
  6. 2025Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variationscited by 12
  7. 2022Explainable Artificial Intelligence for Bayesian Neural Networks: Towards trustworthy predictions of ocean dynamicscited by 11
  8. 2024Discover and Mitigate Multiple Biased Subgroups in Image Classifierscited by 11
  9. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  10. 2025ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generationcited by 11
  11. 2024TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detectioncited by 10
  12. 2024Evaluation of an LLM in Identifying Logical Fallacies: A Call for Rigor When Adopting LLMs in HCI Researchcited by 10
  13. 2024Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanationscited by 10
  14. 2024Benchmark Data Repositories for Better Benchmarkingcited by 10
  15. 2023Pitfalls in Language Models for Code Intelligence: A Taxonomy and Surveycited by 9
  16. 2024On TinyML and Cybersecurity: Electric Vehicle Charging Infrastructure Use Casecited by 9
  17. 2024Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?cited by 9
  18. 2025Can AI Model the Complexities of Human Moral Decision-Making? A Qualitative Study of Kidney Allocation Decisionscited by 9
  19. 2025The Singapore Consensus on Global AI Safety Research Prioritiescited by 9
  20. 2023Reproducibility of Machine Learning: Terminology, Recommendations and Open Issuescited by 8
  21. 2024Machine Learning Robustness: A Primercited by 8
  22. 2024Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Processcited by 8
  23. 2024Towards Building Specialized Generalist AI with System 1 and System 2 Fusioncited by 8
  24. 2024Brain-inspired Artificial Intelligence: A Comprehensive Reviewcited by 8
  25. 2024FairDgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive Learningcited by 8
  26. 2026Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomaliescited by 8
  27. 2026Quantifying Trust: Financial Risk Management for Trustworthy AI Agentscited by 8
  28. 2022A Theoretical Framework for AI Models Explainability with Application in Biomedicinecited by 7
  29. 2023Travel Demand Forecasting: A Fair AI Approachcited by 7
  30. 2023A Survey on Trustworthy Edge Intelligence: From Security and Reliability To Transparency and Sustainabilitycited by 7
  31. 2025Are generative models fair? A study of racial bias in dermatological image generationcited by 7
  32. 2025Toward Robust Non-Transferable Learning: A Survey and Benchmarkcited by 7
  33. 2025Building Trustworthy Multimodal AI: A Review of Fairness, Transparency, and Ethics in Vision-Language Taskscited by 7
  34. 2024Generating Likely Counterfactuals Using Sum-Product Networkscited by 6
  35. 2024Active Fourier Auditor for Estimating Distributional Properties of ML Modelscited by 6
  36. 2024Out-Of-Distribution Detection with Diversification (Provably)cited by 6
  37. 2025Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyondcited by 6
  38. 2025DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Surveycited by 6

50 most cited of 206 All 206 (JSON)