The relationship between trust in AI and trustworthy machine learning technologies
Open accessThe DOI matches its Crossref record; 91 of the 91 references it cites were found in a registry or an index.
Abstract
To design and develop AI-based systems that users and the larger public can justifiably trust, one needs to understand how machine learning technologies impact trust. To guide the design and implementation of trusted AI-based systems, this paper provides a systematic approach to relate considerations about trust from the social sciences to trustworthiness technologies proposed for AI-based services and products. We start from the ABI+ (Ability, Benevolence, Integrity, Predictability) framework augmented with a recently proposed mapping of ABI+ on qualities of technologies that support trust. We consider four categories of trustworthiness technologies for machine learning, namely these for Fairness, Explainability, Auditability and Safety (FEAS) and discuss if and how these support the required qualities. Moreover, trust can be impacted throughout the life cycle of AI-based systems, and we therefore introduce the concept of Chain of Trust to discuss trustworthiness technologies in all stages of the life cycle. In so doing we establish the ways in which machine learning technologies support trusted AI-based systems. Finally, FEAS has obvious relations with known frameworks and therefore we relate FEAS to a variety of international 'principled AI' policy and technology frameworks that have emerged in recent years.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Current academic and public discourses are predominantly structured around the guiding principles towards trustworthy AI [62, 64]”
From Designing for Responsible Trust in AI Systems: A Communication Perspective (2022) · cites this paper as [62]
In the citing paper
“These earlier models have later been adapted to the context of human-technology, human-automation, and human-AI relations (Toreini et al., 2020;Siau & Wang, 2018;Hoff & Bashir, 2015;Schaefer et al., 2016;Riegelsberger et al., 2005;Kaplan et al., 2023;R. Yang & Wibowo, 2022).”
From Trust, distrust, and appropriate reliance in (X)AI: A conceptual clarification of user trust and survey of its empirical evaluation (2025) · cites this paper as Toreini et al., 2020
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Reinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · cited 1×
“, [75, 80] and the unified framework for local explainers which generalises these and other existing methods [64]), global explainers (e.”
BackgroundLearning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 1×
“Supervised Learning algorithms are mainly used in object recognition [54], machine translation [83], filtering spams [32], etc.”
Method"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Jain, A. K., Murty, M. N., & Flynn, P. J. (1999) · ACM Computing Surveys · doi:10.1145/331499.331504 · Cited by 13,199 · cited 1×
“that takes xas input and detects a hidden pattern representation as output, y. The problems that unsupervised learning tackles include grouped a dataset based on a similarity metric (a.k.a clustering [48]), projecting data to a reduced dimension space (e.g. PCA methods [53]) and pre{training algorithms for the other t…”
MethodGauriat, C.-M., Pencolé, Y., Ribot, P., & Brouillet, G. (2024) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.4230/oasics.dx.2024.27 · Cited by 12,586
An integrative model of organizational trust
Mayer, R. C., Davis, J. H., & Schoorman, F. D. (1995) · The Academy of Management Review · doi:10.2307/258792 · Cited by 10,736 · cited 5×
“While each of the attributes are related and may reinforce one another they are also separable [67].”
BackgroundMethodInfluentialIntriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143 · cited 1×
“These meth-ods deal only with data, but it is also relevant to consider integrity during the execution of the algorithm, e.g., in the training stage [26, 13, 11, 61, 85].”
BackgroundDeep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578 · cited 1×
“Careless preparation of the stored data would leak information to an attacker [61] but confidentiality can be enhanced in many ways, for instance through approaches for differential privacy [1, 34], homomorphic encryption [47] or cryptography integrated in machine learning algorithms [79].”
Background
Research works printed but not linked: 11
- [6] Susan Athey and Guido W Imbens. Machine learning methods for estimating heterogeneous causal effects. stat , 1050(5):1-26, 2015. -
- [9] Robert Bartlett, Adair Morse, Richard Stanton, and Nancy Wallace. Consumer-Lending Discrimination in the Era of FinTech. Unpublished working paper. University of California, Berkeley , 2018. -
- [34] Cynthia Dwork. Differential privacy. Encyclopedia of Cryptography and Security , pages 338-340, 2011. -
- [36] Dumitru Erhan, Yoshua Bengio, Aaron Courville, Pierre-Antoine Manzagol, Pascal Vincent, and Samy Bengio. Why does unsupervised pretraining help deep learning? Journal of Machine Learning Research , 11(Feb):625-660, 2010. -
- [38] Jessica Fjeld, Hannah Hilligoss, Nele Achten, Maia Levy Daniel, Sally Kagay, and Joshua Feldman. Principled Artificial Intelligence: Mapping Consensus and Divergence in Ethical and Rights-Based Approaches. 2019. -
- [41] Carlos Adriano Gon¸ calves, Celia Talma Gon¸ calves, Rui Camacho, and Eugenio C Oliveira. The impact of Pre-Processing on the Classification of MEDLINE Documents. Pattern Recognition in Information Systems, Proceedings of the 10th International Workshop on Pattern Recognition in Information Systems, PRIS 2010, In conjunction with ICEIS 2010 , page 10, 2010. -
- [54] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems , pages 1097-1105, 2012. -
- [60] Zachary C Lipton. The mythos of model interpretability. arXiv preprint arXiv:1606.03490 , 2016. - · arXiv
- [68] Donald Michie, David J Spiegelhalter, C C Taylor, and others. Machine learning. Neural and Statistical Classification , 13, 1994. -
- [70] Arvind Narayanan. Translation tutorial: 21 fairness definitions and their politics. In Proc. Conf. Fairness Accountability Transp., New York, USA , 2018. -
- [92] Brian Wynne. A reflexive view of the expert-lay knowledge divide. Risk, environment and modernity: Towards a new ecology , 40:44, 1996. -
Cited by
Items 201–300 of 373
(2024) · Economics and Environmental Management · doi:10.17586/2310-1172-2024-17-4-83-93 · Cited by 6
“В проведенном E. Торейни и др. мета-анализе выделяются следующие принципы этичного искусственного интеллекта: справедливость, объяснимость, проверяемость и надежность [24].”
A mathematical model of the hidden feedback loop effect in machine learning systems
Veprikov, A., Afanasyev, A., & Khritankov, A. (2025) · Knowledge and Information Systems · doi:10.1007/s10115-025-02560-w · Cited by 6
“One of the key quality attributes of trustworthy ML systems [7–9] and socially responsible AI (SRA) algorithms [10] is their ability to behave the way users expect without any unintended side effects.”
Jensen, T., Theofanos, M. F., Greene, K. K., Williams, O., Goad, K., & Fofang, J. S. B. E. (2024) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1609/aies.v7i1.31667 · Cited by 10
“…beliefs can ensure that AI systems are human-centered (Jensen 2021), as suggested for improving the understandability of explanations of AI output (Toreini et al. 2020) and mitigating “anthropo-morphic bias” that occurs when individuals attribute intent to AI systems (Jacovi et al. 2023).”
A leap of faith: building the trust in human biobanks
Zhang, Y., Liao, B., & Lei, R. (2023) · Frontiers in Genetics · doi:10.3389/fgene.2023.1261623 · Cited by 6
Gharbaoui, O. E., Boukhari, H. E., & Salmi, A. (2024) · Innovative Marketing · doi:10.21511/im.20(3).2024.18 · Cited by 8
Artificial Intelligence and Concerns About the Future: A Case Study in Norway
Kalimeri, K., & Tjøstheim, I. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-50344-4_20 · Cited by 12
Schlicker, N., Lechner, F., Wehrle, K., Greulich, B., Hirsch, M. C., & Langer, M. (2025) · Technology Mind and Behavior · doi:10.1037/tmb0000164 · Cited by 8
A Methodological Study of Human-Computer Interaction: A Review
Dhakecha, H. (2022) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2022.46127 · Cited by 5
E-BART: Jointly Predicting and Explaining Truthfulness.
Brand, E., Roitero, K., Soprano, M., & Demartini, G. (2021) · Institutional Research Information System (University of Udine) · Cited by 10
Yang, X., Man, D., Yun, K., Zhang, S., & Han, X. (2023) · Research Square · doi:10.21203/rs.3.rs-3493725/v1 · Cited by 6
Constant, A., Westermann, H., Wilson, B., Kiefer, A. B., Hipólito, I., Pronovost, S., Swanson, S., Albarracin, M., & Ramstead, M. J. D. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.18537 · Cited by 8
“This scepticism may hinder the adoption of AI solutions and stifle ethical innovation (Kożuch & Sienkiewicz-Małyjurek, 2022; Toreini et al., 2019).”
BackgroundBenchmarking Trust: A Metric for Trustworthy Machine Learning
Rutinowski, J., Klüttermann, S., Endendyk, J., Reining, C., & Müller, E. (2024) · Communications in Computer and Information Science · doi:10.1007/978-3-031-63787-2_15 · Cited by 4
“Some works focus primarily on the notion of explainability concerning human understanding [1,16,29,34,48].”
InfluentialTrust Formation in Healthcare AI: An Exploration of Older Adults’ Perspectives
Çelik, Ö., Kulla, M., & Stypińska, J. (2025) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1609/aies.v8i1.36566 · Cited by 4
Hwang, H., Kim, J., Kim, H., Min, H., & Park, K. (2025) · Applied Sciences · doi:10.3390/app152111342 · Cited by 4
Effects of AI explanations on trust and reliance: a study in job shop scheduling
Saßmannshausen, T. M., Burggräf, P., Hassenzahl, M., & Sauer, C. R. (2026) · Ergonomics · doi:10.1080/00140139.2026.2634115 · Cited by 4
The Black-Box Syndrome: Embracing Randomness in Machine Learning Models
Anthis, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-11647-6_1 · Cited by 4
Social Transparency in Network Monitoring and Security Systems
Soroko, D., Savino, G.-L., Gray, N., & Schöning, J. (2023) · International Conference on Mobile and Ubiquitous Multimedia (MUM) · doi:10.1145/3626705.3627773 · Cited by 4
“Trust as a concept is still subject of debate, even when it comes to the definition [36, 60], let alone ways of building, measuring and reporting it [17, 46, 52, 88, 91, 95].”
BackgroundShould You Trust Your Voice Assistant? It’s Complicated, but No
Stamatiou, F., & Karakonstantis, X. (2024) · Linköping electronic conference proceedings · doi:10.3384/ecp208015 · Cited by 5
“…[11], [12], [13], [14], [15], a lot of work has been published on specific issues, such as the relationship between trust and trustworthiness [16], the possibility of trusting robots [17], [18], the relationship between trust and distrust [19], as well as empirical studies on trust in hybrid…”
BackgroundAI Literacy on Human-Centered Considerations
Ng, D. T. K., Leung, J. K. L., Su, M. J., Yim, I. H. Y., Qiao, M. S., & Chu, S. K. W. (2022) · Springer eBooks · doi:10.1007/978-3-031-18880-0_9 · Cited by 4
A Conceptual Model for Implementing Explainable AI by Design: Results of an Empirical Study
Berg, M. V. D., Kuiper, O. X., van der Haas, Y. J., Gerlings, J., Sent, D., & Leijnen, S. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia230075 · Cited by 6
Maccaro, A., Pagliara, S. M., Zarro, M., Piaggio, D., Abdulsalami, F., Su, W., Haleem, M. S., & Pecchia, L. (2023) · Scientific Reports · doi:10.1038/s41598-023-39834-8 · Cited by 6
Human-AI Teaming: Following the IMOI Framework
Kleanthous, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-60611-3_27 · Cited by 6
Mapping dominant AI schools to multiple accountability types
Elliott, M. T. J., Deepak, P., & MacCárthaigh, M. (2025) · Transforming Government People Process and Policy · doi:10.1108/tg-11-2024-0272 · Cited by 4
Song, Y., Zhang, S., Wang, Y., & Shi, Z. (2025) · Modelling and Simulation in Engineering · doi:10.1155/mse/5998003 · Cited by 5
“This fi eld utilizes wearable inertial measurement unit (IMU) sensors [19] and machine learning [20] techniques to classify human movements.”
Behind the Screen: Investigating ChatGPT’s Dark Personality Traits and Conspiracy Beliefs
Rutinowski, J., Weber, E., & Pauly, M. (2026) · Human Behavior and Emerging Technologies · doi:10.1155/hbe2/7230525 · Cited by 4
Explainability e auditability: interpretando e validando modelos de machine learning
Silva, W., Oliveira, V., Araújo, S. S., Vieira, D., & Castro, M. (2022) · doi:10.5753/sbc.11014.1.3 · Cited by 4
Rosales, A., Malanowska, A., Araghi, T. K., Kuribayashi, M., Kowalczyk, M., Blanche, D., Mazurczyk, W., & Megías, D. (2024) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1145/3664476.3670934 · Cited by 4
“The premise of trustworthiness is that maintaining trust in digital systems is pivotal for securing the acceptance and adoption of those technologies [28].”
Towards Trustworthy Edge Intelligence: Insights from Voice-Activated Services
Toussaint, W., & Ding, A. Y. (2022) · IEEE International Conference on Services Computing · doi:10.1109/scc55611.2022.00043 · Cited by 7
“[20] introduce the notion of a Chain of Trust in machine learning (ML).”
BackgroundTrusted Partners: Human-Machine Teaming and the Future of Military AI
Konaev, M., Huang, T. C., & Chahal, H. (2021) · doi:10.51593/20200024 · Cited by 8
Building Legal DatasetsPreprint
Soh, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.02034 · Cited by 4
“Even assuming we care solely about economic value, profits, while presumably correlated with F1 score-type performance metrics, turn also on variables like user adoption and trust [28, 9, 15].”
BackgroundBridging the Divide: A Systems Thinking Approach to Inclusivity in AI Development and EducationPreprint
Sarkar, A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5097669 · Cited by 5
Ethics Without Teeth? Challenges and Opportunities in AI Declarations for Platform Governance
Haidar, A. (2026) · Journal of theoretical and applied electronic commerce research · doi:10.3390/jtaer21040103 · Cited by 3
A Conceptual Crosswalk Between Trustworthy Records and Trustworthy AI
Carrasco, L. B., Engvall, T. S., & Dobslaw, F. (2026) · Philosophy & Technology · doi:10.1007/s13347-026-01112-6 · Cited by 3
“A few articles described trustworthiness as an attribute of being worthy of trust (Ferrario, 2025; Kaur et al., 2022; Toreini et al., 2020), or “what´s required for people to trust AI” (Liao & Sundar, 2022).”
Using It but Not Trusting It: Technology Acceptance and Generative AI in European Fact-Checking
Dierickx, L., & van Dalen, A. (2026) · Emerging Media · doi:10.1177/27523543261449974 · Cited by 3
“…that trust is a prerequisite for the use of AI technology, considering that it supports seamless interaction and decision-making, enabling effective human – machine collaboration (e.g., Omrani et al., 2022; Scharowski et al., 2023; Schmidt et al., 2020; Siau & Wang, 2018; Toreini et al., 2020).”
Guzij, K., Fröhlich, M., Fincke, F., Schmidt, A., & Alt, F. (2022) · Designing Interactive Systems Conference · doi:10.1145/3532106.3533462 · Cited by 3
“Being antecedents to trust, the three most relevant trustworthiness beliefs are competence, benevolence, and integrity [31, 32, 57, 62, 71, 74, 84, 85].”
BackgroundThe Ethical Consideration of Using Artificial Intelligence (AI) in Medicine
Komalasari, R. (2022) · Advances in healthcare information systems and administration book series · doi:10.4018/978-1-6684-5656-9.ch001 · Cited by 5
Schuitemaker, N., van Vliet, M., Brinkkemper, S., van de Weerd, I., & España, S. (2024) · Lecture notes in business information processing · doi:10.1007/978-3-031-61007-3_24 · Cited by 3
Do You Trust AI? Examining AI Trustworthiness Perceptions Among the General Public
Batut, A., Prudhomme, L., van Sambeek, M., & Chen, W. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-60611-3_2 · Cited by 4
Lu, M., Li, Z., & Gao, J. (2025) · Journal of X-Ray Science and Technology · doi:10.1177/08953996241308175 · Cited by 3
“23 However, medical imaging data is complex, and advanced techniques are often needed to identify subtle patterns that traditional evaluations might miss. Advances in deep learning, particularly through convolutional neural networks (CNNs), have enabled the extraction of intricate imaging features…”
Re-calibrating Machine Learning Models Using Confidence Interval Bounds
Campagner, A., Famiglini, L., & Cabitza, F. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-13448-7_11 · Cited by 4
Babbage, C. M., Wagner, H., Dowthwaite, L., Portillo, V., Vallejos, E. P., & Fischer, J. E. (2024) · Internet Interventions · doi:10.1016/j.invent.2024.100740 · Cited by 4
“As privacy violations or misuse of personal data are one of the main concerns related to trust in technologies (Toreini et al., 2020), it is not surprising similar concerns were also highlighted with the COVID-19 app (Williams et al., 2020).”
On Fairness and InterpretabilityPreprint
Deepak, P., Sanil, & Jose, J. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.13271 · Cited by 5
Kazim, E., Polle, R., Carvalho, G., Koshiyama, A., Inness, C., Knight, A., Gorski, C., Barber, D., Lomas, E., Yılmaz, E., et al. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3935987 · Cited by 3
Dippold, D. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.10694 · Cited by 3
Towards Explainable Metaheuristic: Mining Surrogate Fitness Models for Importance of VariablesPreprint
Singh, M., Brownlee, A. E. I., & Cairns, D. R. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.14135 · Cited by 3
“day-to-day life has brought with it ethics concerns[42], and a lack of trust from those users directly impacted by the automated decision making [2, 38].”
BackgroundTrust, but Verify: Using Self-supervised Probing to Improve Trustworthiness
Deng, A., Shen, L., Xiong, M., Chen, Z., & Hooi, B. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19778-9_21 · Cited by 5
“However, the ever-growing range of applications of neural networks has also led to increasing concern about the reliability and trustworthiness of their decisions [32,17], especially in safety-critical domains such as autonomous driving and medical diagnosis.”
BackgroundArtificial Intelligence in Education: A Preliminary Study
Saifudin, N. A. M. E., Anwar, N., Hashim, H., & Kurniawan, Y. (2024) · Open Journal of Social Sciences · doi:10.4236/jss.2024.1211039 · Cited by 2
“As discovered by many researchers, the interaction be-tween AI services and products with other technologies and systems affects the level of trust based on continuous integration, interoperability, and the ability to enhance rather than disrupt existing services and products (Toreini et al., 2020).”
Trust Paradoxes in Machine Learning: An Ontological Approach
Ding, Y., Herbaut, N., & Salinesi, C. (2025) · Lecture notes in business information processing · doi:10.1007/978-3-031-94590-8_10 · Cited by 2
Newen, C., Bodemer, D., Glantz, S., Müller, E., Wischnewski, M., & Schnaubert, L. (2025) · Proceedings · doi:10.1109/icdm65498.2025.00070 · Cited by 2
“Furthermore, attempts to map trust onto guidelines for trustworthy machine-learning technologies focus on principles such as fairness, explainability, audibility, and safety [46].”
Lee, M. H. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3798377 · Cited by 3
“Complementing these findings, research on accountable and trustworthy AI emphasizes governance mechanisms, such as over-sight, contestability, auditing, and responsibility across deployment [20, 30, 35, 36, 38, 43, 44].”
Building Trustworthy AI Systems for Condition Monitoring
Hämäläinen, A., Karhinen, A., & Viitala, R. (2026) · IEEE Access · doi:10.1109/access.2026.3688909 · Cited by 4
“Stages of model setup and usage (inference) related to a traditional machine learning pipeline as identified by Toreini et al. [13].”
InfluentialLiao, M., Lee, S., Dooley, A., Xiong, A., & Sundar, S. S. (2026) · Media Psychology · doi:10.1080/15213269.2026.2659876 · Cited by 2
Araujo, T. (2026) · AI & Society · doi:10.1007/s00146-026-03279-0 · Cited by 3
“…robustness and safety, privacy and data governance, transparency (and explainabil-ity), diversity, non-discrimination and fairness, societal and environmental wellbeing, and accountability, with other taxonomies focusing on a subset of these concepts (e.g., Toreini et al. 2019; Kaur et al. 2022).”
DenseHMM: Learning Hidden Markov Models by Learning Dense Representations
Sicking, J., Pintz, M., Akila, M., & Wirtz, T. (2022) · International Conference on Pattern Recognition Applications and Methods · doi:10.5220/0010821800003122 · Cited by 2
Partially Monotonic Learning for Neural Networks
Trindade, J., Vinagre, J., Fernandes, K., Paiva, N., & Jorge, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-74251-5_2 · Cited by 2
“However, according to Rudin [11], the use of post-hoc methods perpetuates a bad practice, which can cause damage to society in high-risk scenarios and, therefore, the in-model approach is more adequate to ensure trustworthy AI [14].”
BackgroundResponsibility and Regulation: Exploring Social Measures of Trust in Medical AI
McGarry, G., Crabtree, A., Chamberlain, A., & Urquhart, L. (2024) · International Symposium on Trustworthy Autonomous Systems (TAS) · doi:10.1145/3686038.3686041 · Cited by 2
“This obligation is driving a second wave of research that attempts to interpret, study, and understand just how to do RI [13], insights which are largely absent from principled frameworks related to AS [1, 9, 28].”
Counterfactual Gradients-based Quantification of Prediction Trust in Neural Networks
Prabhushankar, M., & AlRegib, G. (2024) · IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr62202.2024.00091 · Cited by 3
“The authors in [1] identify four attributes of trustworthiness that impact the trust in AI systems.”
BackgroundBridging Data and Clinical Insight: Explainable AI for ICU Mortality Risk Prediction
Hassan, A. H., bin Sulaiman, R., Abdulhak, M., & Kahtan, H. (2025) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2025.0160275 · Cited by 3
“XAI controls the complexity of user explanations to those that a medical practitioner can understand, thus helping in forming opinions that can be acted on and trusted [29], [30], [31].”
The Impact of Personality on the Adoption of Biometric Technology
Wolverton, C. C., Hollier, B. N. G., Cahyanto, I., & Davis, D. (2025) · Information Systems Management · doi:10.1080/10580530.2025.2477451 · Cited by 3
“Reliability (Toreini et al., 2020), transparency (Ribeiro et al., 2016), fairness (Binns, 2018), and ethical considerations (Cabiddu et al., 2022) impact trust in AI.”
Analysis of Trustworthiness in Machine Learning and Deep Learning
Kentour, M., & Lu, J. (2021) · Huddersfield Research Portal (University of Huddersfield) · Cited by 6
The Influencing Factors of Human-Machine Trust: A Behavioral Science Perspective
Cai, H., Wang, C., & Zhu, Y. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-9492-9_212 · Cited by 2
Improved Explainability through Uncertainty Estimation in Automatic Target Recognition of SAR Images
Blomerus, N., de Villiers, P., & Nel, W. (2021) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion49465.2021.9627066 · Cited by 2
“These ML algorithms make decisions without any logical explanation to how the output was derived [10], which causes scepticism from the users as well as a lack of trust.”
BackgroundBärmann, S. (2022) · Forschung und Praxis an der FHWien der WKW · doi:10.1007/978-3-658-36861-6_8 · Cited by 3
Manziuk, E. (2022) · Computer Systems and Information Technologies · doi:10.31891/csit-2022-1-11 · Cited by 2
Metaverse: Fission the architecture
Zaman, A., Abir, M. R., Reaj, M. A. H., & Sakib, T. H. (2024) · International Journal of Science and Research Archive · doi:10.30574/ijsra.2024.12.1.0808 · Cited by 1
Role of Computational Science and Artificial Intelligence in Understanding Climate Change
Thakur, A., Kumar, A., Singh, K., & Raina, P. (2026) · Springer eBooks · doi:10.1007/978-981-97-9859-9_83 · Cited by 1
Naserameri, M., & Rilling, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.20918 · Cited by 1
Examining media coverage of ethical dimensions of advanced algorithmic technology
Vilchez, A., Bera, S., Lewenstein, B. V., & Hilgartner, S. (2026) · Public Understanding of Science · doi:10.1177/09636625261419755 · Cited by 1
“The media plays a crucial role in shaping the public’s imaginary of AATs (Hansen, 2022) and is central to fostering trust, acceptance, and the eventual adoption of emerging technologies (Toreini et al., 2020).”
Lin, J., & Powell, N. L. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2636791 · Cited by 1
Suk, J., & Zhang, Y. (2026) · Journal of Broadcasting & Electronic Media · doi:10.1080/08838151.2026.2694048 · Cited by 1
Manziuk, E., Barmak, O., Radiuk, P., Kuznetsov, V., & Krak, I. V. (2024) · International Workshop of IT-professionals on Artificial Intelligence (ProfIT AI) · doi:10.55056/ceur-ws.org/vol-3777/paper25.pdf · Cited by 3
“A number of works [12, 24–26] focus on investigating individual dimensions of reliability, such as safety, transparency, fairness, or explainability.”
An Interpretable Graph-Based Mapping of Trustworthy Machine Learning Research
Derzsy, N., Majumdar, S., & Malik, R. (2021) · Springer proceedings in complexity · doi:10.1007/978-3-030-81854-8_7 · Cited by 1
“This sub-field of ML is often referred by umbrella terms such as Responsible ML or Trustworthy ML [3,30,32].”
BackgroundExplainable AI; Are we there yet?
Tanwar, N., & Hasija, Y. (2022) · IEEE Delhi Section Conference (DELCON) · doi:10.1109/delcon54057.2022.9752777 · Cited by 1
“Even more generally, the supervised method is put forward in labeled data; nevertheless, it is more suitable to use an unsupervised method before or in place of the supervised method [25].”
MethodU-trustworthy Models. Reliability, Competence, and Confidence in Decision-Making
Vashistha, R. N., & Farahi, A. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i18.29972 · Cited by 5
AI and Its Importance in the Development of the Luxury Market
Ellahi, A. (2025) · Advances in marketing, customer relationship management, and e-services book series · doi:10.4018/979-8-3693-8542-5.ch016 · Cited by 2
Guermai, R. E., Jamal, A., & Aissaoui, K. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-1737-3.ch002 · Cited by 1
Soriano, A. J. N., & Isa-Jara, R. (2025) · Revista Científica y Tecnológica UPSE · doi:10.26423/rctu.v12i1.885 · Cited by 1
Trustworthy evaluation of large language models
Zhang, X., Ye, H.-J., & Zhan, D. (2025) · Frontiers of Computer Science · doi:10.1007/s11704-025-50442-9 · Cited by 5
Quantitative Understanding of VAE by Interpreting ELBO as Rate Distortion Cost of Transform Coding.Preprint
Nakagawa, A., & Kato, K. (2020) · arXiv (Cornell University) · Cited by 1
Enriching Moral Perspectives on AI: Concepts of Trust amongst AfricansPreprint
Amugongo, L. M., Bidwell, N. J., & Mwatukange, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.14116 · Cited by 3
Evaluating the Impact of Algorithm Confidence Ratings on Human Decision Making in Visual Search
Jones, A. P., Trumbo, M., Matzen, L. E., Stites, M. C., Howell, B. C., Divis, K., & Gastelum, Z. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-78321-1_15
Navigating Through Changes of a Digital World
Hauk, N., & Hauswirth, M. (2021) · Springer eBooks · doi:10.1007/978-3-030-86144-5_37
The role of trustworthiness in automated decision-making systems and the law
Wang, B. T. (2022) · Queensland University of Technology · doi:10.5204/thesis.eprints.231388
DP2Net: Defense Against Adversarial Examples by Detecting Perturbed Pixels
Wang, T., Liu, H., Wang, F., Du, J., & Bao, Y. (2022) · 2022 7th International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/icsip55141.2022.9886169
“The powerful technology will intensify people’s reliance on it, so that the wrong judgment caused by adversarial examples will lead to more and more serious consequences, making deep neural networks lack trustworthiness in safety-critical areas and causing great concern [6].”
BackgroundVisual Analytics for Explainable and Trustworthy Machine Learning
Chatzimparmpas, A. (2023) · doi:10.15626/lud.482.2023
Yang, X., Man, D., Yun, K., Zhang, S., & Han, X. (2023) · doi:10.2196/preprints.46626
Ernawati, D. P., Kurniadi, A., Said, A., Anjani, S., & Isworo, S. (2023) · Asian Journal of Medicine and Health · doi:10.9734/ajmah/2023/v21i8836
Implications of the Instruments View of Computer Simulation
Alvarado, R. (2023) · Synthese Library/Synthese library · doi:10.1007/978-3-031-38647-3_7
Introduction to How to Design and Develop a Business Research Project
Cambré, B., Elliott, K., & Fierens, J. (2023) · Edward Elgar Publishing eBooks · doi:10.4337/9781035307845.00007
Self-citationDreslin, B. D., Office of Workforce Development for Teachers & Scientists (WDTS) USDOE Office of Science (SC), & Baweja, J. A. (2023) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.2172/1999810 · Cited by 2
Peer Review #1 of "A step toward building a unified framework for managing AI bias (v0.1)"
(2023) · PeerJ Computer Science · doi:10.7287/peerj-cs.1630v0.1/reviews/1
Peer Review #2 of "A step toward building a unified framework for managing AI bias (v0.1)"
(2023) · PeerJ Computer Science · doi:10.7287/peerj-cs.1630v0.1/reviews/2
Peer Review #2 of "A step toward building a unified framework for managing AI bias (v0.2)"
(2023) · PeerJ Computer Science · doi:10.7287/peerj-cs.1630v0.2/reviews/2
Peer Review #2 of "A step toward building a unified framework for managing AI bias (v0.3)"
(2023) · PeerJ Computer Science · doi:10.7287/peerj-cs.1630v0.3/reviews/2
Medical Use of Intelligent Systems
Komalasari, R. (2023) · Jurnal Berkala Kesehatan · doi:10.20527/jbk.v9i2.14593
New Proportion Measures of Discrimination Based on Natural Direct and Indirect Effects
Shingaki, R., & Kuroki, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-63735-3_10
Vertrauensbildende Maßnahmen am Beispiel von KI-Anwendungen in der Hochschulbildung
Schork, S. (2024) · Springer eBooks · doi:10.1007/978-3-658-43816-6_11
Ramteke, V., Pramod, D., & Patil, K. P. (2024) · Smart innovation, systems and technologies · doi:10.1007/978-981-97-5081-8_5
Masciotra, V., & Boudrias, J. (2024) · Ad machina l avenir de l humain au travail · doi:10.1522/radm.no8.1840
Metadata
- Authors
- Toreini, E., Aitken, M., Coopamootoo, K., Elliott, K., Zelaya, C. G., & van Moorsel, A.
- Affiliations
- Newcastle University (GB)
- Newcastle University, United Kingdom
- Venue
- Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency
- Publisher
- ACM
- Published
- 2020-01-27
- Pages
- 272-283
- OpenAlex
- W2990399168
- Cited by
- 296
- References
- 89
- Citations by year
- 2026: 24 · 2025: 56 · 2024: 57 · 2023: 63 · 2022: 53 · 2021: 30 · 2020: 13
- FWCI
- 41.23
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Durham Research Online (Durham University) (submittedVersion, cc-by)
- University of Birmingham Research Portal (University of Birmingham) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Engineering and Physical Sciences Research Council (EP/R033595/1)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Safety Systems Engineering in Autonomy
- Keywords
- trust in AI, trustworthy machine learning, fairness, explainability, auditability, safety, trust chain, AI lifecycle
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.