{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T18:40:04Z","timestamp":1780598404730,"version":"3.54.1"},"reference-count":60,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T00:00:00Z","timestamp":1770595200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Artificial intelligence (AI) powers breakthroughs in language processing, computer vision, and scientific discovery; yet, the increasing complexity of frontier models makes their reasoning opaque. This opacity undermines public trust, complicates deployment in safety-critical settings, and frustrates compliance with emerging regulations. In response to initiatives such as the White House AI Action Plan, we synthesize the scientific foundations and policy landscape for interpretability, control, and robustness. We clarify key concepts and survey intrinsically interpretable and post-hoc explanation techniques, discuss human-centered evaluation and governance, and analyze how adversarial threats and distributional shifts motivate robustness research. An empirical case study compares logistic regression, random forests, and gradient boosting on a synthetic dataset with a binary-sensitive attribute using accuracy, F1 score, and group-fairness metrics, and illustrates trade-offs between performance and fairness. We integrate ethical and policy perspectives, including recommendations from America\u2019s AI Action Plan and recent civil rights frameworks, and conclude with guidance for researchers, practitioners, and policymakers on advancing trustworthy AI.<\/jats:p>","DOI":"10.3390\/a19020136","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T08:15:54Z","timestamp":1770624954000},"page":"136","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Investing in AI Interpretability, Control, and Robustness"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8849-4521","authenticated-orcid":false,"given":"Maikel","family":"Leon","sequence":"first","affiliation":[{"name":"Department of Business Technology, Miami Herbert Business School, University of Miami, Coral Gables, FL 33146, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,9]]},"reference":[{"key":"ref_1","first-page":"274","article-title":"United States \u00b7 Winning the AI Race? The US AI Action Plan in Context","volume":"2","author":"Hine","year":"2025","journal-title":"J. Law Regul."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Kim, J., Maathuis, H., and Sent, D. (2024). Human-centered evaluation of explainable AI applications: A systematic review. Front. Artif. Intell., 7.","DOI":"10.3389\/frai.2024.1456486"},{"key":"ref_3","unstructured":"Baker, S., and Xiang, W. (2023). Explainable AI is Responsible AI: How Explainability Creates Trustworthy and Socially Responsible Artificial Intelligence. arXiv."},{"key":"ref_4","first-page":"15411","article-title":"Holistic Adversarial Robustness of Deep Learning Models","volume":"37","author":"Chen","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"102620","DOI":"10.1016\/j.is.2025.102620","article-title":"GPT-5 and open-weight large language models: Advances in reasoning, transparency, and control","volume":"136","author":"Leon","year":"2026","journal-title":"Inf. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Leslie, D. (2020). Explaining Decisions Made with AI. SSRN Electron. J.","DOI":"10.2139\/ssrn.4033308"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1111\/chso.12915","article-title":"Artificial intelligence for children: UNICEF\u2019s policy guidance and beyond","volume":"39","author":"Liu","year":"2024","journal-title":"Child. Soc."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Deck, L., Schoeffer, J., De-Arteaga, M., and K\u00fchl, N. (2024). A Critical Survey on Fairness Benefits of Explainable AI. FAccT \u201924: Proceedings of the 2024 ACM Conference on Fairness Accountability and Transparency, ACM.","DOI":"10.1145\/3630106.3658990"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Brandl, S., Bugliarello, E., and Chalkidis, I. (2024). On the Interplay between Fairness and Explainability. Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024), Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.trustnlp-1.10"},{"key":"ref_10","first-page":"1","article-title":"Adversarial Resilience in Deep Learning: Challenges, Defense Mechanisms, and Future Directions","volume":"13","year":"2025","journal-title":"J. Recent Trends Comput. Sci. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Warren, G., Shklovski, I., and Augenstein, I. (2025). Show Me the Work: Fact-Checkers\u2019 Requirements for Explainable Automated Fact-Checking. CHI \u201925: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, ACM.","DOI":"10.1145\/3706598.3713277"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Shivadekar, S. (2025). Cognitive Artificial Intelligence for Health and Climate: Deep Models, Interpretability, and Decision Support, Deep Science Publishing.","DOI":"10.70593\/978-93-7185-745-1"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kabir, S., Hossain, M.S., and Andersson, K. (2025). A Review of Explainable Artificial Intelligence from the Perspectives of Challenges and Opportunities. Algorithms, 18.","DOI":"10.3390\/a18090556"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Pushkarna, M., Zaldivar, A., and Kjartansson, O. (2022). Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI. FAccT \u201922: Proceedings of the 2022 ACM Conference on Fairness Accountability and Transparency, ACM.","DOI":"10.1145\/3531146.3533231"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Hutchinson, B., Smart, A., Hanna, A., Denton, R., Greer, C., Kjartansson, O., Barnes, P., and Mitchell, M. (2021). Towards Accountability for Machine Learning Datasets: Practices from Software Engineering and Infrastructure. FAccT \u201921: Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, ACM.","DOI":"10.1145\/3442188.3445918"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Nathim, K.W., Hameed, N.A., Salih, S.A., Taher, N.A., Salman, H.M., and Chornomordenko, D. (2024). Ethical AI with Balancing Bias Mitigation and Fairness in Machine Learning Models. Proceedings of the 2024 36th Conference of Open Innovations Association (FRUCT), IEEE.","DOI":"10.23919\/FRUCT64283.2024.10749873"},{"key":"ref_17","first-page":"4049","article-title":"FairCoRe: Fairness-aware Recommendation through Counterfactual Representation Learning","volume":"37","author":"Bin","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3641276","article-title":"Should Fairness be a Metric or a Model? A Model-based Framework for Assessing Bias in Machine Learning Pipelines","volume":"42","author":"Lalor","year":"2024","journal-title":"ACM Trans. Inf. Syst."},{"key":"ref_19","first-page":"1","article-title":"Fairness-Aware Graph Neural Networks: A Survey","volume":"18","author":"Chen","year":"2024","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kats, J. (2025). Machine Learning Detection of IPKVM Exploitation in Online Exam Environments. Proceedings of the 2025 IEEE Opportunity Research Scholars Symposium (ORSS), IEEE.","DOI":"10.1109\/ORSS66051.2025.11121637"},{"key":"ref_21","first-page":"7639","article-title":"Explanation Consistency Training: Facilitating Consistency-Based Semi-Supervised Learning with Interpretability","volume":"35","author":"Han","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"19899","DOI":"10.1038\/s41598-022-24356-6","article-title":"Using model explanations to guide deep learning models towards consistent explanations for EHR data","volume":"12","author":"Watson","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"DeSimone, H. (2024). Explainable AI: The Quest for Transparency in Business and Beyond. Proceedings of the 2024 7th International Conference on Information and Computer Technologies (ICICT), IEEE.","DOI":"10.1109\/ICICT62343.2024.00093"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"David, R., Shankar, H., Kura, P., Kowtarapu, K., S, U.M., and Karkuzhali, S. (2025). Advancement in Explainable AI: Bringing Transparency and Interpretability to Machine Learning Models for Use in High-Stakes Decisions. Proceedings of the 2025 International Conference on Emerging Smart Computing and Informatics (ESCI), IEEE.","DOI":"10.1109\/ESCI63694.2025.10988079"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Kruschel, S., Hambauer, N., Weinzierl, S., Zilker, S., Kraus, M., and Zschech, P. (2025). Challenging the Performance-Interpretability Trade-Off: An Evaluation of Interpretable Machine Learning Models. Bus. Inf. Syst. Eng.","DOI":"10.1007\/s12599-024-00922-2"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1108\/JOSM-05-2024-0223","article-title":"Why should I trust you? Influence of explanation design on consumer behavior in AI-based services","volume":"36","author":"Nizette","year":"2024","journal-title":"J. Serv. Manag."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e70071","DOI":"10.1111\/ejss.70071","article-title":"Towards Explainable AI: Interpreting Soil Organic Carbon Prediction Models Using a Learning-Based Explanation Method","volume":"76","author":"Kakhani","year":"2025","journal-title":"Eur. J. Soil Sci."},{"key":"ref_28","first-page":"859","article-title":"Unlocking the black box: An in-depth review on interpretability, explainability, and reliability in deep learning","volume":"37","author":"Arslan","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"15751","DOI":"10.1007\/s13369-024-09896-5","article-title":"Transparency in Diagnosis: Unveiling the Power of Deep Learning and Explainable AI for Medical Image Interpretation","volume":"50","author":"Garg","year":"2025","journal-title":"Arab. J. Sci. Eng."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1007\/s10639-022-11221-2","article-title":"Explainable AI and machine learning: Performance evaluation and explainability of classifiers on educational data mining inspired career counseling","volume":"28","author":"Guleria","year":"2022","journal-title":"Educ. Inf. Technol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1572","DOI":"10.1038\/s42256-025-01084-w","article-title":"Mechanistic understanding and validation of large AI models with SemanticLens","volume":"7","author":"Dreyer","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1038\/s41597-023-01974-x","article-title":"Evaluating explainability for graph neural networks","volume":"10","author":"Agarwal","year":"2023","journal-title":"Sci. Data"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3583558","article-title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","volume":"55","author":"Nauta","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Tak, A.N., Banayeeanzade, A., Bolourani, A., Kian, M., Jia, R., and Gratch, J. (2025). Mechanistic Interpretability of Emotion Inference in Large Language Models. Proceedings of the Findings of the Association for Computational Linguistics: ACL 2025, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2025.findings-acl.679"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1038\/s41598-025-30899-1","article-title":"Explainable AI and echo state networks calibrate trust in human-machine interaction","volume":"16","author":"Hao","year":"2026","journal-title":"Sci. Rep."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Marusich, L.R., Files, B.T., Bancilhon, M., Rawal, J.C., and Raglin, A. (2025). Trust Calibration for Joint Human\/AI Decision-Making in Dynamic and Uncertain Contexts. Artificial Intelligence in HCI, Springer Nature.","DOI":"10.1007\/978-3-031-93412-4_6"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1943","DOI":"10.1007\/s43681-024-00577-5","article-title":"A systematic review of fairness in machine learning","volume":"5","author":"Rabonato","year":"2024","journal-title":"AI Ethics"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Ashurst, C., and Weller, A. (2023). Fairness Without Demographic Data: A Survey of Approaches. EAAMO \u201923: Proceedings of the Equity and Access in Algorithms, Mechanisms, and Optimization, ACM.","DOI":"10.1145\/3617694.3623234"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"100862","DOI":"10.1016\/j.cosrev.2025.100862","article-title":"Cognitive mapping variants and their training algorithms","volume":"59","author":"Leon","year":"2026","journal-title":"Comput. Sci. Rev."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Remtulla, R., Samet, A., Kulbay, M., Akdag, A., Hocini, A., Volniansky, A., Kahn Ali, S., and Qian, C.X. (2025). A Future Picture: A Review of Current Generative Adversarial Neural Networks in Vitreoretinal Pathologies and Their Future Potentials. Biomedicines, 13.","DOI":"10.3390\/biomedicines13020284"},{"key":"ref_41","first-page":"1","article-title":"Adversarial Robustness of Neural Networks from the Perspective of Lipschitz Calculus: A Survey","volume":"57","author":"Kudenko","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Chen, J., Yan, H., Liu, B., Zhao, S., Chen, X., Li, Z., and Xu, H. (2025). Erasing backdoor of deep neural networks using neural perturbation-based attention distillation. Int. J. Model. Simul. Sci. Comput., 16.","DOI":"10.1142\/S1793962325500369"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Tabassi, E. (2023). Artificial Intelligence Risk Management Framework (AI RMF 1.0), National Institute of Standards and Technology.","DOI":"10.6028\/NIST.AI.100-1"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1871","DOI":"10.1007\/s00146-023-01635-y","article-title":"Accountability in artificial intelligence: What it is and how it works","volume":"39","author":"Novelli","year":"2023","journal-title":"AI Soc."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1038\/s41591-024-02838-6","article-title":"Generative models improve fairness of medical classifiers under distribution shifts","volume":"30","author":"Ktena","year":"2024","journal-title":"Nat. Med."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"113522","DOI":"10.1016\/j.asoc.2025.113522","article-title":"Deep Wavelet Self-Attention Non-negative Tensor Factorization for non-linear analysis and classification of fMRI data","volume":"182","author":"Wang","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"122853","DOI":"10.1016\/j.eswa.2023.122853","article-title":"Unsupervised deep frequency-channel attention factorization to non-linear feature extraction: A case study of identification and functional connectivity interpretation of Parkinson\u2019s disease","volume":"243","author":"Ke","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"2040","DOI":"10.30574\/ijsra.2024.13.2.2396","article-title":"Data privacy in the era of AI: Navigating regulatory landscapes for global businesses","volume":"13","author":"Mbah","year":"2024","journal-title":"Int. J. Sci. Res. Arch."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"78994","DOI":"10.1109\/ACCESS.2023.3294569","article-title":"A Review of Trustworthy and Explainable Artificial Intelligence (XAI)","volume":"11","author":"Chamola","year":"2023","journal-title":"IEEE Access"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Weaver, J.F. (2025). AI Bill of Rights and creative lawmaking. Research Handbook on the Law of Artificial Intelligence, Edward Elgar Publishing.","DOI":"10.4337\/9781035316496.00009"},{"key":"ref_51","first-page":"4","article-title":"An AI Bill of Rights: Implications for Health Care AI and Machine Learning\u2014A Bioethics Lens","volume":"23","year":"2022","journal-title":"Am. J. Bioeth."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1007\/s00146-022-01499-8","article-title":"Artificial intelligence with American values and Chinese characteristics: A comparative analysis of American and Chinese governmental AI policies","volume":"39","author":"Hine","year":"2022","journal-title":"AI Soc."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"3265","DOI":"10.1007\/s43681-024-00653-w","article-title":"AI governance: A systematic literature review","volume":"5","author":"Batool","year":"2025","journal-title":"AI Ethics"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"444","DOI":"10.37394\/23202.2024.23.46","article-title":"The Escalating AI\u2019s Energy Demands and the Imperative Need for Sustainable Solutions","volume":"23","author":"Leon","year":"2024","journal-title":"Wseas Trans. Syst."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1007\/s44206-023-00036-4","article-title":"The Ethics of Artificial Intelligence for Intelligence Analysis: A Review of the Key Challenges with Recommendations","volume":"2","author":"Blanchard","year":"2023","journal-title":"Digit. Soc."},{"key":"ref_56","first-page":"1058","article-title":"The right to contest automated decisions under the General Data Protection Regulation: Beyond the so-called \u201cright to explanation\u201d","volume":"16","year":"2021","journal-title":"Regul. Gov."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1016\/j.ins.2022.12.012","article-title":"Prolog-based agnostic explanation module for structured pattern classification","volume":"622","author":"Napoles","year":"2023","journal-title":"Inf. Sci."},{"key":"ref_58","first-page":"1","article-title":"XAI-Eval: A framework for comparative evaluation of explanation methods in healthcare","volume":"11","author":"Agrawal","year":"2025","journal-title":"Digit. Health"},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"1","DOI":"10.25046\/aj100201","article-title":"Generative Artificial Intelligence and Prompt Engineering: A Comprehensive Guide to Models, Methods, and Best Practices","volume":"10","author":"Leon","year":"2025","journal-title":"Adv. Sci. Technol. Eng. Syst. J."},{"key":"ref_60","unstructured":"Bilal, A., Ebert, D., and Lin, B. (2025). LLMs for Explainable AI: A Comprehensive Survey. arXiv."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/2\/136\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T08:27:59Z","timestamp":1770625679000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/2\/136"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,9]]},"references-count":60,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["a19020136"],"URL":"https:\/\/doi.org\/10.3390\/a19020136","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,9]]}}}