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].”
BackgroundAn Introduction to Kernel and Nearest-Neighbor Nonparametric Regression
Altman, N. S. (1992) · The American Statistician · doi:10.1080/00031305.1992.10475879 · Cited by 5,708 · cited 1×
“e notion of a machine learning pipeline. 3.1 Basics of Machine Learning A machine learning algorithm is basically a function as y= f (x) (with exception of a few algorithms such as nearest{neighbour [4]). In this equation, f represents the function that maps input to the output, i.e. the machine learning model. In thi…”
BackgroundInfluentialLipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427 · cited 2×
“Lipton [60] provides a thorough discussion on these terms and the differences.”
BackgroundBasic concepts and taxonomy of dependable and secure computing
Avizienis, A., Laprie, J.-C., Randell, B., & Landwehr, C. (2004) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2004.2 · Cited by 5,223 · cited 1×
“t, and, specically, identify trust-enabling machine learning technologies. AI and machine learning approaches are trustworthy if they have properties that one is justied to place trust in them (see [7] for this manner of phrasing). In the context of the FAT* conference, it is important to highlight the dierence betwee…”
BackgroundDwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012) · Proceedings of the 3rd Innovations in Theoretical Computer Science Conference · doi:10.1145/2090236.2090255 · Cited by 3,501 · cited 1×
“• Fairness Technologies: technologies focused on detection or prevention of discrimination and bias in different demographics [98, 63, 77, 97, 55, 23, 49, 37, 46, 25, 50, 96, 35].”
BackgroundSelection of relevant features and examples in machine learning
Blum, A. L., & Langley, P. (1997) · Artificial Intelligence · doi:10.1016/s0004-3702(97)00063-5 · Cited by 3,298 · cited 1×
“• Explainability Technologies: technologies focused on explaining and interpreting the outcome to the stakeholders (including end-users) in a humane manner [6, 60, 17, 41, 86, 33, 19, 42, 76, 62, 89, 69].”
BackgroundTowards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121 · cited 1×
“[31] suggested two types of explainability, namely explainability of an application (e.”
BackgroundLearning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761 · cited 1×
“, [75, 80] and the unified framework for local explainers which generalises these and other existing methods [64]), global explainers (e.”
BackgroundMethods for interpreting and understanding deep neural networks
Montavon, G., Samek, W., & Müller, K.-R. (2018) · Digital Signal Processing · doi:10.1016/j.dsp.2017.10.011 · Cited by 2,665 · cited 2×
“There are many challenges left with respect to explainable machine learning technologies, including trading off fidelity to the original model and explainability [69].”
BackgroundWhy Does Unsupervised Pre-training Help Deep Learning?
Erhan, D., Bengio, Y., Courville, A. C., Manzagol, P.-A., Vincent, P., & Bengio, S. (2010) · Journal of Machine Learning Research · Cited by 2,631
Equality of Opportunity in Supervised Learning
Hardt, M., Price, E., & Srebro, N. (2016) · arXiv · doi:10.48550/arxiv.1610.02413 · Cited by 2,536 · cited 2×
“• Fairness Technologies: technologies focused on detection or prevention of discrimination and bias in different demographics [98, 63, 77, 97, 55, 23, 49, 37, 46, 25, 50, 96, 35].”
BackgroundWood, S. N. (2003) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/1467-9868.00374 · Cited by 2,445 · cited 1×
“• Explainability Technologies: technologies focused on explaining and interpreting the outcome to the stakeholders (including end-users) in a humane manner [6, 17, 19, 33, 41, 42, 60, 62, 69, 76, 86, 89].”
BackgroundPrivacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813687 · Cited by 2,356 · cited 2×
“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].”
BackgroundFeature selection in machine learning: A new perspective
Cai, J., Luo, J., Wang, S., & Yang, S. (2018) · Neurocomputing · doi:10.1016/j.neucom.2017.11.077 · Cited by 2,061 · cited 1×
“cluding end-users) in a humane manner [6, 17, 19, 33, 41, 42, 60, 62, 69, 76, 86, 89].”
Certifying and Removing Disparate Impact
Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., & Venkatasubramanian, S. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783311 · Cited by 1,827 · cited 1×
“• Fairness Technologies: technologies focused on detection or prevention of discrimination and bias in different demographics [98, 63, 77, 97, 55, 23, 49, 37, 46, 25, 50, 96, 35].”
BackgroundMisunderstood misunderstanding: social identities and public uptake of science
Wynne, B. (1992) · Public Understanding of Science · doi:10.1088/0963-6625/1/3/004 · Cited by 1,675
Support vector machines for spam categorization
Drucker, H., Wu, D., & Vapnik, V. N. (1999) · IEEE Transactions on Neural Networks · doi:10.1109/72.788645 · Cited by 1,471 · cited 1×
“translation [83], filtering spams [32], etc.”
Kusner, M. J., Loftus, J. R., Russell, C., & Silva, R. (2017) · arXiv · doi:10.48550/arxiv.1703.06856 · Cited by 995 · cited 1×
“• Fairness Technologies: technologies focused on detection or prevention of discrimination and bias in different demographics [98, 63, 77, 97, 55, 23, 49, 37, 46, 25, 50, 96, 35].”
BackgroundWynne, B. (2006) · Public Health Genomics · doi:10.1159/000092659 · Cited by 972 · cited 1×
“Rather, in many cases the public adopts an ambivalent form of trust – described by Wynne [93, 91, 92] as an: as if trust.”
BackgroundRivest, R. L. (1987) · Machine Learning · doi:10.1007/bf00058680 · Cited by 886 · cited 2×
“• Explainability Technologies: technologies focused on explaining and interpreting the outcome to the stakeholders (including end-users) in a humane manner [6, 60, 17, 41, 86, 33, 19, 42, 76, 62, 89, 69].”
Fairness-Aware Classifier with Prejudice Remover Regularizer
Kamishima, T., Akaho, S., Asoh, H., & Sakuma, J. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33486-3_3 · Cited by 694 · cited 1×
“[50] proposed a model–specific approach by adding a regulating term for a logistic regression classifier, which eventually leads to unbiased classification.”
Trust Repair After An Organization-Level Failure
Gillespie, N., & Dietz, G. (2009) · Academy of Management Review · doi:10.5465/amr.2009.35713319 · Cited by 681 · cited 1×
“They are opportunities to forge new relationships with stakeholders (positive or negative) [40].”
BackgroundThe impact of preprocessing on text classification
Uysal, A. K., & Gunal, S. (2014) · Information Processing & Management · doi:10.1016/j.ipm.2013.08.006 · Cited by 657
Oblivious multi-party machine learning on trusted processors
Ohrimenko, O., Schuster, F., Fournet, C., Mehta, A., Nowozin, S., Vaswani, K., & Costa, M. (2016) · MPG.PuRe (Max Planck Society) · Cited by 647
Li, X., Hess, T. J., & Valacich, J. S. (2008) · The Journal of Strategic Information Systems · doi:10.1016/j.jsis.2008.01.001 · Cited by 635 · cited 8×
“Interestingly, they recognised 47 qualities, categorised them into eight groups, which are a combination of the qualities identified by Siau [59], i.e., hu-mane (promotion of human values, professional responsibility, human control of technology) and technological qualities (fairness and non–discrimination, trans-paren…”
BackgroundInfluentialZafar, M. B., Valera, I., Gomez Rodriguez, M., & Gummadi, K. P. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052660 · Cited by 632 · cited 1×
“• Fairness Technologies: technologies focused on detection or prevention of discrimination and bias in different demographics [98, 63, 77, 97, 55, 23, 49, 37, 46, 25, 50, 96, 35].”
BackgroundA Survey of Methods for Explaining Black Box Models
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2019) · ACM Computing Surveys · doi:10.1145/3236009 · Cited by 629 · cited 1×
“intelligibility,comprehensibility and interpretability are often used interchangeably [43].”
Measuring trust inside organisations
Dietz, G., & Den Hartog, D. N. (2006) · Personnel Review · doi:10.1108/00483480610682299 · Cited by 596 · cited 5×
“Building on the work of Mayer et al [67], Dietz and Den Hartog [29] outline three forms of trust: trust as a belief; a decision and; an action.”
BackgroundMethodInfluentialAccurate intelligible models with pairwise interactions
Lou, Y., Caruana, R., Gehrke, J., & Hooker, G. (2013) · Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2487575.2487579 · Cited by 564 · cited 1×
“cluding end-users) in a humane manner [6, 17, 19, 33, 41, 42, 60, 62, 69, 76, 86, 89].”
Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
Hu, W., & Tan, Y. (2022) · Communications in Computer and Information Science · doi:10.1007/978-981-19-8991-9_29 · Cited by 547
SoK: Security and Privacy in Machine Learning
Papernot, N., McDaniel, P., Sinha, A., & Wellman, M. P. (2018) · 2018 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2018.00035 · Cited by 502 · cited 3×
“The security and privacy foundations of a ML model is not different from classical security model of Confidentiality, Integrity and Availability (CIA model [73]).”
BackgroundMethodSupport Vector Machines Under Adversarial Label Noise
Biggio, B., Nelson, B. A., & Laskov, P. (2011) · UNICA IRIS Institutional Research Information System (University of Cagliari) · Cited by 454
The Measure and Mismeasure of Fairness
Corbett-Davies, S., Gaebler, J. D., Nilforoshan, H., Shroff, R., & Goel, S. (2018) · arXiv · doi:10.48550/arxiv.1808.00023 · Cited by 444 · cited 1×
“• Fairness Technologies: technologies focused on detection or prevention of discrimination and bias in different demographics [98, 63, 77, 97, 55, 23, 49, 37, 46, 25, 50, 96, 35].”
BackgroundSoK: Towards the Science of security and privacy in machine learning
Papernot, N., McDaniel, P. D., Sinha, A., & Wellman, M. P. (2018) · Singapore Management University Institutional Knowledge (InK) (Singapore Management University) · Cited by 427
Cross-Cultural Differences in Relationship- and Group-Based Trust
Yuki, M., Maddux, W. W., Brewer, M. B., & Takemura, K. (2005) · Personality and Social Psychology Bulletin · doi:10.1177/0146167204271305 · Cited by 422 · cited 1×
“[95] discussed such cultural impact on the trust establishment pattern.”
BackgroundA Survey on Security Threats and Defensive Techniques of Machine Learning: A Data Driven View
Liu, Q., Li, P., Zhao, W., Cai, W., Yu, S., & Leung, V. C. M. (2018) · IEEE Access · doi:10.1109/access.2018.2805680 · Cited by 421 · cited 2×
“and possibly repairing tampered data [14, 12, 58]. These methods 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]. 6 Conclusion This paper established the connection between trust as a notion within the social sci…”
BackgroundSecurity Evaluation of Pattern Classifiers under Attack
Biggio, B., Fumera, G., & Roli, F. (2014) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2013.57 · Cited by 411
The Role and Limits of Principles in AI Ethics: Towards a Focus on Tensions
Whittlestone, J., Nyrup, R., Alexandrova, A., & Cave, S. (2019) · Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3306618.3314289 · Cited by 399 · cited 1×
“es of the involved science and technology, but do not go into the specics of technical implementation guidelines. There is emerging literature reviewing Principled AI frameworks. Whittlestone et al. [88] provide a critical analysis of frameworks for ethical machine learning and highlights a number of challenges, some…”
Background(2018) · Singapore Management University Institutional Knowledge (InK) (Singapore Management University) · Cited by 390
Generating Adversarial Malware Examples for Black-Box Attacks Based on GANPreprint
Hu, W., & Tan, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.05983 · Cited by 361 · 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].”
BackgroundMeasuring user confidence in smartphone security and privacy
Chin, E., Felt, A. P., Sekar, V., & Wagner, D. (2012) · Proceedings of the Eighth Symposium on Usable Privacy and Security · doi:10.1145/2335356.2335358 · Cited by 347 · cited 1×
“situations that their data is being collected [22].”
BackgroundANTIDOTE: understanding and defending against poisoning of anomaly detectors
Rubinstein, B. I. P., Nelson, B., Huang, L., Joseph, A. D., Lau, S.-H., Rao, S., Taft, N., & Tygar, J. D. (2009) · Proceedings of the 9th ACM SIGCOMM conference on Internet measurement · doi:10.1145/1644893.1644895 · Cited by 331 · cited 1×
“• Safety Technologies: technologies focused on ensuring the operation of the model as intended in presence of active or passive malicious attacker [14, 73, 16, 15, 78, 56, 79, 71].”
BackgroundPublic Deliberation and Governance: Engaging with Science and Technology in Contemporary Europe
Hagendijk, R., & Irwin, A. (2006) · Minerva · doi:10.1007/s11024-006-0012-x · Cited by 303
Provenance management in curated databases
Buneman, P., Chapman, A., & Cheney, J. (2006) · Proceedings of the 2006 ACM SIGMOD international conference on Management of data · doi:10.1145/1142473.1142534 · Cited by 297 · cited 1×
“It involves proposals on how to store provenance data [18, 20, 21, 74, 94], summarisation of provenance data [2, 28, 66], specific query language for the provenance data [28], query explainability [8, 10], Natural language processing for prove-”
BackgroundA multidisciplinary survey on discrimination analysis
Romei, A., & Ruggieri, S. (2014) · The Knowledge Engineering Review · doi:10.1017/s0269888913000039 · Cited by 288 · cited 2×
“ch of which demonstrates the importance of continuous trust as discussed in Section 2.4. First, stages may impact on each other in terms of the level of trust they are able to propagate. Romei et al. [77] reviewed various cases studies that led to biased decisions and analysed the causes. There is an important specic…”
BackgroundInfluentialYes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection
Demontis, A., Melis, M., Biggio, B., Maiorca, D., Arp, D., Rieck, K., Corona, I., Giacinto, G., & Roli, F. (2019) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2017.2700270 · Cited by 288 · cited 1×
“, in the training stage [26, 13, 11, 61, 85].”
Measuring discrimination in algorithmic decision making
Žliobaitė, I. (2017) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-017-0506-1 · Cited by 272 · cited 2×
“• Fairness Technologies: technologies focused on detection or prevention of discrimination and bias in different demographics [98, 63, 77, 97, 55, 23, 49, 37, 46, 25, 50, 96, 35].”
Backgroundk-NN as an implementation of situation testing for discrimination discovery and prevention
Luong, B. T., Ruggieri, S., & Turini, F. (2011) · Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2020408.2020488 · Cited by 263
Conscientious Classification: A Data Scientist's Guide to Discrimination-Aware Classification
d'Alessandro, B., O'Neil, C., & LaGatta, T. (2017) · Big Data · doi:10.1089/big.2016.0048 · Cited by 195 · cited 1×
“• Fairness Technologies: technologies focused on detection or prevention of discrimination and bias in different demographics [98, 63, 77, 97, 55, 23, 49, 37, 46, 25, 50, 96, 35].”
BackgroundTowards the Science of Security and Privacy in Machine Learning
Papernot, N., McDaniel, P. D., Sinha, A., & Wellman, M. P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.03814 · Cited by 192
Chapman, A. P., Jagadish, H. V., & Ramanan, P. (2008) · Proceedings of the 2008 ACM SIGMOD international conference on Management of data · doi:10.1145/1376616.1376715 · Cited by 190 · cited 1×
“It involves proposals on how to store provenance data [18, 20, 21, 74, 94], summarisation of provenance data [2, 28, 66], specific query language for the provenance data [28], query explainability [8, 10], Natural language processing for prove-”
BackgroundMultiple classifier systems for robust classifier design in adversarial environments
Biggio, B., Fumera, G., & Roli, F. (2010) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-010-0007-7 · Cited by 187 · cited 1×
“, in the training stage [26, 13, 11, 61, 85].”
A study of the effects of preprocessing strategies on sentiment analysis for Arabic text
Duwairi, R., & El-Orfali, M. (2014) · Journal of Information Science · doi:10.1177/0165551514534143 · Cited by 178 · cited 1×
“cluding end-users) in a humane manner [6, 17, 19, 33, 41, 42, 60, 62, 69, 76, 86, 89].”
Verifying computations without reexecuting them
Walfish, M., & Blumberg, A. J. (2015) · Communications of the ACM · doi:10.1145/2641562 · Cited by 164 · cited 1×
“nance data [27, 90] and cryptographic solutions to verify model’s behaviours without exposing user privacy [72] or revealing model‘s intellectual properties [87].”
BackgroundBishop, M. (2007) · IEEE Security & Privacy · doi:10.1109/msp.2007.159 · Cited by 161 · cited 1×
“• Safety Technologies: technologies focused on ensuring the operation of the model as intended in presence of active or passive malicious attacker [14, 73, 16, 15, 78, 56, 79, 71].”
BackgroundTrusting Intelligent Machines: Deepening Trust Within Socio-Technical Systems
Andras, P., Esterle, L., Guckert, M., Han, T. A., Lewis, P. R., Milanovic, K., Payne, T., Perret, C., Pitt, J., Powers, S. T., et al. (2018) · IEEE Technology and Society Magazine · doi:10.1109/mts.2018.2876107 · Cited by 153 · cited 1×
“[5] summarise some of the ways that trust has been approached across different disciplines: “In the social world trust is about the expectation of cooperative, supportive, and non-hostile behaviour.”
BackgroundBagging Classifiers for Fighting Poisoning Attacks in Adversarial Classification Tasks
Biggio, B., Corona, I., Fumera, G., Giacinto, G., & Roli, F. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-21557-5_37 · Cited by 146 · cited 1×
“, in the training stage [26, 13, 11, 61, 85].”
Security Evaluation of Support Vector Machines in Adversarial Environments
Biggio, B., Corona, I., Nelson, B. A., Rubinstein, B. I. P., Maiorca, D., Fumera, G., Giacinto, G., & Roli, F. (2014) · Springer eBooks · doi:10.1007/978-3-319-02300-7_4 · Cited by 144
Towards Explaining the Effects of Data Preprocessing on Machine Learning
Gonzalez Zelaya, C. V. (2019) · 2019 IEEE 35th International Conference on Data Engineering (ICDE) · doi:10.1109/icde.2019.00245 · Cited by 139 · cited 1×
“• Explainability Technologies: technologies focused on explaining and interpreting the outcome to the stakeholders (including end-users) in a humane manner [6, 60, 17, 41, 86, 33, 19, 42, 76, 62, 89, 69].”
Decision Provenance: Harnessing Data Flow for Accountable Systems
Singh, J., Cobbe, J., & Norval, C. (2019) · IEEE Access · doi:10.1109/access.2018.2887201 · Cited by 110
Aitken, M., Cunningham-Burley, S., & Pagliari, C. (2016) · Science and Public Policy · doi:10.1093/scipol/scv075 · Cited by 107 · cited 2×
“standing of science, on the assumption that, where the public is sceptical or mistrusting, this can be explained by ignorance or lack of understanding, and as such can be ‘corrected’ through better dissemination of scientific knowledge or facts [3]).”
BackgroundSelf-citationApproximate lineage for probabilistic databases
Ré, C., & Suciu, D. M. (2008) · Proceedings of the VLDB Endowment · doi:10.14778/1453856.1453943 · Cited by 94 · cited 1×
“It involves proposals on how to store provenance data [18, 20, 21, 74, 94], summarisation of provenance data [2, 28, 66], specific query language for the provenance data [28], query explainability [8, 10], Natural language processing for prove-”
BackgroundSafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud
Ghodsi, Z., Gu, T., & Garg, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.10268 · Cited by 87 · cited 1×
“Much of the literature around auditability relates to data provenance research in database and cloud concepts [44] and model provenance approaches [39].”
BackgroundPublic Knowledge and Public Trust
Cunningham‐Burley, S. (2006) · Public Health Genomics · doi:10.1159/000092658 · Cited by 85 · cited 1×
“However, such approaches are now widely discredited as it is recognised that they overlook the role of members of the public in actively engaging with scientific knowledge rather than being “passive recipients of scientific knowledge” [24, p. 206].”
BackgroundA framework for quantitative security analysis of machine learning
Laskov, P., & Kloft, M. (2009) · Proceedings of the 2nd ACM workshop on Security and artificial intelligence · doi:10.1145/1654988.1654990 · Cited by 62 · cited 1×
“Integrity can be enhanced by either preventing tampering, such as in pre-processing [73], or by discovering and possibly repairing tampered data [12, 14, 58].”
BackgroundQuery-Based Why-Not Provenance with NedExplain
Bidoít, N., Herschel, M., & Tzompanaki, K. (2014) · doi:10.5441/002/edbt.2014.14 · Cited by 62 · cited 2×
“It involves proposals on how to store provenance data [18, 20, 21, 74, 94], summarisation of provenance data [2, 28, 66], specific query language for the provenance data [28], query explainability [8, 10], Natural language processing for provenance data [27, 90] and cryptographic solutions to verify model’s behaviours…”
BackgroundA statistical framework for fair predictive algorithms
Lum, K., & Johndrow, J. E. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.08077 · Cited by 57 · cited 1×
“• Fairness Technologies: technologies focused on detection or prevention of discrimination and bias in different demographics [98, 63, 77, 97, 55, 23, 49, 37, 46, 25, 50, 96, 35].”
BackgroundProvenance as Dependency Analysis
Cheney, J., Ahmed, A. J., & Acar, U. A. (2007) · Springer eBooks · doi:10.1007/978-3-540-75987-4_10 · Cited by 56
Rawlsian Fairness for Machine Learning.Preprint
Joseph, M., Kearns, M. J., Morgenstern, J., Neel, S., & Roth, A. (2016) · arXiv (Cornell University) · Cited by 56
SubZero: A fine-grained lineage system for scientific databases
Wu, E., Madden, S. R., & Stonebraker, M. R. (2013) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde.2013.6544881 · Cited by 51 · cited 2×
“It involves proposals on how to store provenance data [18, 20, 21, 74, 94], summarisation of provenance data [2, 28, 66], specific query language for the provenance data [28], query explainability [8, 10], Natural language processing for provenance data [27, 90] and cryptographic solutions to verify model’s behaviours…”
BackgroundApproximated Summarization of Data Provenance
Ainy, E., Bourhis, P., Davidson, S. B., Deutch, D., & Milo, T. (2015) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2806416.2806429 · Cited by 41 · cited 1×
“It involves proposals on how to store provenance data [18, 20, 21, 74, 94], summarisation of provenance data [2, 28, 66], specific query language for the provenance data [28], query explainability [8, 10], Natural language processing for prove-”
BackgroundEvaluation of a Hybrid Approach for Efficient Provenance Storage
Xie, Y., Muniswamy‐Reddy, K., Feng, D., Li, Y., & Long, D. D. E. (2013) · ACM Transactions on Storage · doi:10.1145/2501986 · Cited by 39 · cited 2×
“It involves proposals on how to store provenance data [18, 20, 21, 74, 94], summarisation of provenance data [2, 28, 66], specific query language for the provenance data [28], query explainability [8, 10], Natural language processing for provenance data [27, 90] and cryptographic solutions to verify model’s behaviours…”
BackgroundSelective provenance for datalog programs using top-k queries
Deutch, D., Gilad, A., & Moskovitch, Y. (2015) · Proceedings of the VLDB Endowment · doi:10.14778/2824032.2824039 · Cited by 38 · cited 1×
“It involves proposals on how to store provenance data [18, 20, 21, 74, 94], summarisation of provenance data [2, 28, 66], specific query language for the provenance data [28], query explainability [8, 10], Natural language processing for prove-”
Background(2015) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 34
Curie: A method for protecting SVM Classifier from Poisoning Attack
Laishram, R., & Phoha, V. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.01584 · Cited by 32 · cited 1×
“• Safety Technologies: technologies focused on ensuring the operation of the model as intended in presence of active or passive malicious attacker [14, 73, 16, 15, 78, 56, 79, 71].”
BackgroundThe recovery of trust: case studies of organisational failures and trust repair
Dietz, G., & Gillespie, N. A. (2012) · Cited by 24
Interpretable & Explorable Approximations of Black Box Models
Lakkaraju, H., Kamar, E., Caruana, R., & Leskovec, J. (2017) · arXiv · doi:10.48550/arxiv.1707.01154 · Cited by 23 · cited 1×
“growing body of literature, including local explainers (e.g., [75, 80] and the unied framework for local explainers which generalises these and other existing methods [64]), global explainers (e.g., [57]). There are many challenges left with respect to explainable machine learning technologies, including trading o del…”
BackgroundInfluentialLocal clustering in provenance graphs
Macko, P., Margo, D., & Seltzer, M. (2013) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2505515.2505624 · Cited by 15 · cited 1×
“It involves proposals on how to store provenance data [18, 20, 21, 74, 94], summarisation of provenance data [2, 28, 66], specific query language for the provenance data [28], query explainability [8, 10], Natural language processing for prove-”
BackgroundDeutch, D., Frost, N., & Gilad, A. (2016) · Proceedings of the VLDB Endowment · doi:10.14778/3007263.3007303 · Cited by 10 · cited 2×
“It involves proposals on how to store provenance data [18, 20, 21, 74, 94], summarisation of provenance data [2, 28, 66], specific query language for the provenance data [28], query explainability [8, 10], Natural language processing for provenance data [27, 90] and cryptographic solutions to verify model’s behaviours…”
BackgroundOn Debugging Non-Answers in Keyword Search Systems
Baid, A., Wu, W., Sun, C., Doan, A., & Naughton, J. F. (2015) · Movebank · doi:10.5441/002/edbt.2015.05 · Cited by 9 · cited 2×
“It involves proposals on how to store provenance data [18, 20, 21, 74, 94], summarisation of provenance data [2, 28, 66], specific query language for the provenance data [28], query explainability [8, 10], Natural language processing for provenance data [27, 90] and cryptographic solutions to verify model’s behaviours…”
BackgroundDiscrimination in Algorithmic Decision Making: From Principles to Measures and Mechanisms
Zafar, M. B. (2019) · MPG.PuRe (Max Planck Society) · doi:10.22028/d291-27726 · Cited by 6 · cited 1×
“• Fairness Technologies: technologies focused on detection or prevention of discrimination and bias in different demographics [98, 63, 77, 97, 55, 23, 49, 37, 46, 25, 50, 96, 35].”
BackgroundProvenance in Context of Hadoop as a Service (HaaS) - State of the Art and Research Directions
Gupta, H., Mehta, S., Hans, S., Chatterjee, B., Lohia, P., & Rajmohan, C. (2017) · IEEE ... International Conference on Cloud Computing · doi:10.1109/cloud.2017.91 · Cited by 4 · cited 1×
“system‘s behaviour and its interactions with its inner components or outside entities. 19 Much of the literature around auditability relates to data provenance research in database and cloud concepts [44] and model provenance approaches [39]. It involves proposals on how to store provenance data [18, 20, 21, 74, 94],…”
Background
Research works printed but not linked: 11
- Susan Athey and Guido W Imbens . 2015. Machine learning methods for estimating heterogeneous causal effects. stat 1050, 5 ( 2015 ), 1--26. Susan Athey and Guido W Imbens. 2015. Machine learning methods for estimating heterogeneous causal effects. stat 1050, 5 (2015), 1--26.
- Robert Bartlett , Adair Morse , Richard Stanton , and Nancy Wallace . 2018. Consumer-Lending Discrimination in the Era of FinTech. Unpublished working paper . University of California , Berkeley ( 2018 ). Robert Bartlett, Adair Morse, Richard Stanton, and Nancy Wallace. 2018. Consumer-Lending Discrimination in the Era of FinTech. Unpublished working paper. University of California, Berkeley (2018).
- 10.5555/2040895.2040945 · doi:10.5555/2040895.2040945
- Cynthia Dwork . 2011. Differential privacy. Encyclopedia of Cryptography and Security ( 2011 ), 338--340. Cynthia Dwork. 2011. Differential privacy. Encyclopedia of Cryptography and Security (2011), 338--340.
- Carlos Adriano Gonçalves , Celia Talma Gonçalves , Rui Camacho , and Eugenio C Oliveira . 2010 . 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 (2010), 10. Carlos Adriano Gonçalves, Celia Talma Gonçalves, Rui Camacho, and Eugenio C Oliveira. 2010. 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 (2010), 10.
- Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105. Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.
- Zachary C Lipton . 2016. The mythos of model interpretability. arXiv preprint arXiv:1606.03490 ( 2016 ). Zachary C Lipton. 2016. The mythos of model interpretability. arXiv preprint arXiv:1606.03490 (2016). · arXiv
- Donald Michie , David J Spiegelhalter , C C Taylor , and others. 1994. Machine learning. Neural and Statistical Classification 13 ( 1994 ). Donald Michie, David J Spiegelhalter, C C Taylor, and others. 1994. Machine learning. Neural and Statistical Classification 13 (1994).
- Arvind Narayanan . 2018 . Translation tutorial: 21 fairness definitions and their politics . In Proc. Conf. Fairness Accountability Transp. , New York, USA. Arvind Narayanan. 2018. Translation tutorial: 21 fairness definitions and their politics. In Proc. Conf. Fairness Accountability Transp., New York, USA.
- 10.5555/3305890.3306006 · doi:10.5555/3305890.3306006
- Brian Wynne . 1996. A reflexive view of the expert-lay knowledge divide. Risk, environment and modernity: Towards a new ecology 40 ( 1996 ), 44. Brian Wynne. 1996. A reflexive view of the expert-lay knowledge divide. Risk, environment and modernity: Towards a new ecology 40 (1996), 44.
Cited by
Trustworthy AI: From Principles to Practices
Li, B., Qi, P., Liu, B., Di, S., Liu, J., Pei, J., Yi, J., & Zhou, B. (2023) · ACM Computing Surveys · doi:10.1145/3555803 · Cited by 612
Responsible Artificial Intelligence Governance: A Review and Research Framework
Papagiannidis, E., Mikalef, P., & Conboy, K. (2025) · The Journal of Strategic Information Systems · doi:10.1016/j.jsis.2024.101885 · Cited by 565
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI
Jacovi, A., Marasović, A., Miller, T., & Goldberg, Y. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445923 · Cited by 545
“on between any user and the AI [8, 11, 71, 76]. The recent rapid growth in the field ofexplainable AI (XAI) is also, in part, motivated by the need to maintain trust between the human user and the AI [31, 35, 46, 52, 59, 72]. By designing AI that users can and will trust to interact with, the AI can be safely implemen…”
BackgroundNazar, M., Alam, M. M., Yafi, E., & Su'ud, M. M. (2021) · IEEE Access · doi:10.1109/access.2021.3127881 · Cited by 312
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
Brundage, M., Avin, S., Wang, J., Belfield, H., Krueger, G., Hadfield, G., Khlaaf, H., Yang, J., Toner, H., Fong, R., et al. (2020) · arXiv · doi:10.48550/arxiv.2004.07213 · Cited by 306
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.