Trustworthy AI: From Principles to Practices
Open accessThe DOI matches its Crossref record; 398 of the 399 references it cites were found in a registry or an index; 74 of the 251 sources its claims cite were checked for support.
Abstract
The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, many current AI systems are found vulnerable to imperceptible attacks, biased against underrepresented groups, lacking in user privacy protection. These shortcomings degrade user experience and erode people’s trust in all AI systems. In this review, we provide AI practitioners with a comprehensive guide for building trustworthy AI systems. We first introduce the theoretical framework of important aspects of AI trustworthiness, including robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, and accountability. To unify currently available but fragmented approaches toward trustworthy AI, we organize them in a systematic approach that considers the entire lifecycle of AI systems, ranging from data acquisition to model development, to system development and deployment, finally to continuous monitoring and governance.
Overview
CoChat Summary
TL;DR
This review provides a comprehensive guide to trustworthy AI, organizing robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, and accountability across the AI system lifecycle. It proposes TrustAIOps as a continuous workflow and identifies open challenges including trade-offs, immature evaluation, and risks from large pre-trained models.
Key findings
- The paper defines eight trustworthiness aspects—robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, and accountability—and argues that predictive accuracy alone is insufficient; trustworthiness must be assessed systematically across data preparation, algorithm design, development, deployment, and management.
- It proposes TrustAIOps, extending MLOps/DevOps with aligned trustworthiness principles, interdisciplinary collaboration, extensive artifact management, and continuous feedback loops across the five lifecycle stages.
- It documents frictions and trade-offs: transparency can leak private data or intellectual property and enable targeted hacking; adversarial robustness can reduce accuracy; robustness and fairness can negatively affect each other; and explanations can be fragile, inconsistent with human interpretation, or hard to judge as faithful.
- In privacy evaluation, it cites work showing that 15 demographic attributes were sufficient to render 99% of participants unique.
Methods
- Design: narrative review/survey, not an empirical study; it synthesizes technical, engineering, and governance literature on trustworthy AI.
- Data or sample: no dataset or sample is used; the paper draws on cited literature and industrial case studies of face recognition, autonomous driving, and NLP in the appendix.
- Main analysis: conceptual organization of approaches by trustworthiness aspect and by lifecycle stage, culminating in a proposed systematic framework and TrustAIOps workflow.
Limitations
- The paper states that explainability, transparency, and accountability are still seldom evaluated quantitatively; approaches to robustness and explainability remain immature; trade-offs and frictions exist between trustworthiness aspects; large pre-trained models are costly and difficult to reproduce and may carry bias or privacy leakage; and end-user awareness is limited.
- Evident from the text: as a survey, it presents no original experiments or quantitative validation of the proposed TrustAIOps workflow, and its recommendations are conceptual rather than empirically tested in the paper.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
39 Valid · 28 Not valid · 96 Not checked · 119 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“It is widely recognized that AI models might be vulnerable to attacks by adversaries with malicious intentions.”
What the sources say
- Partly supportedcites [68] [68] Andreas Rossler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, and Matthias Nießner. Faceforensics++: Learning to detect manipulated facial images. In Proceedings of the IEEE/CVF International Conference on Computer Vision , pages 1-11, 2019. - sourceExperimental — accuracy not yet measured
The Face Manipulation Methods section says forgery detectors have robustness issues and that compression and resizing can erase traces they use to detect manipulation. That supports vulnerability in these particular models, but the paper does not establish the broader claim that AI models are vulnerable to intentional attacks by malicious adversaries. (LLM, conf=0.78)
- Not matchedcites [304]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked — no full text of the sourcecites [11] [11] Sarah Bankins and Paul Formosa. Ethical ai at work: The social contract for artificial intelligence and its implications for the workplace psychological contract. Redefining the Psychological Contract in the Digital Era: Issues for Research and Practice , pages 55-72, 2021. - source
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“many current AI systems are found vulnerable to imperceptible attacks, biased against underrepresented groups, lacking in user privacy protection.”
What the sources say
- Could not verifycites [68] [68] Andreas Rossler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, and Matthias Nießner. Faceforensics++: Learning to detect manipulated facial images. In Proceedings of the IEEE/CVF International Conference on Computer Vision , pages 1-11, 2019. - sourceExperimental — accuracy not yet measured
The Face Manipulation Methods section discusses robustness of facial-forgery detectors to compression and resizing, and §4.2.2 reports lower detection performance on compressed videos. Searches for imperceptible adversarial attacks and perturbations found no passage saying that many current AI systems are vulnerable to such attacks. (LLM, conf=0.74)
- Not matchedcites [304]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not checked — no full text of the sourcecites [11] [11] Sarah Bankins and Paul Formosa. Ethical ai at work: The social contract for artificial intelligence and its implications for the workplace psychological contract. Redefining the Psychological Contract in the Digital Era: Issues for Research and Practice , pages 55-72, 2021. - source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, liveness detection is still vulnerable against new types of attacks by fake videos generated by AI techniques like DeepFake [54].”
What the sources say
- Partly supportedcites [54] [54] Thanh Thi Nguyen, Quoc Viet Hung Nguyen, Cuong M Nguyen, Dung Nguyen, Duc Thanh Nguyen, and Saeid Nahavandi. Deep learning for deepfakes creation and detection: A survey. arXiv preprint arXiv:1909.11573 , 2019. - sourceExperimental — accuracy not yet measured
Section 3, “Deepfake Detection,” reports that tested face-recognition systems failed to detect deepfakes effectively and that other methods had high error rates on a newly produced deepfake-video dataset. This supports vulnerability to AI-generated fake videos, but the passage does not specifically assess liveness detection. (LLM, conf=0.84)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Research has shown that face recognition systems can be easily spoofed by impersonation attackers wearing a small printed adversarial patch [90, 30, 43, 73].”
What the sources say
- Supportedcites [90] [90] Zihao Xiao, Xianfeng Gao, Chilin Fu, Yinpeng Dong, Wei Gao, Xiaolu Zhang, Jun Zhou, and Jun Zhu. Improving transferability of adversarial patches on face recognition with generative models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages 11845-11854, 2021. - source
The Introduction describes adversarial eyeglass frames used to impersonate another identity and says physical patches can fool face-recognition models. Section 4.5 reports an attacker wearing printed adversarial eyeglass frames and finding that the patches retained high transferability after printing and photographing. The physical-world experiment involved one volunteer and three target identities. (LLM, conf=0.86)
- Partly supportedcites [30] [30] Ying Guo, Xingxing Wei, Guoqiu Wang, and Bo Zhang. Meaningful adversarial stickers for face recognition in physical world. arXiv:2104.06728 , 2021. - sourceExperimental — accuracy not yet measured
Section 5.3 reports successful impersonation attacks using facial stickers and shows examples in the physical world. But Section 3.5 explicitly says the method does not involve printing: subjects wear existing stickers placed according to calculated attack parameters. Thus the paper supports the impersonation point, but not the description of a printed adversarial patch. (LLM, conf=0.89)
- Partly supportedcites [43] [43] Stepan Komkov and Aleksandr Petiushko. Advhat: Real-world adversarial attack on arcface face id system. In 2020 25th International Conference on Pattern Recognition (ICPR) , pages 819-826. IEEE, 2021. - sourceExperimental — accuracy not yet measured
The Abstract and Introduction (p. 1) describe an easily reproducible attack using a printed sticker on a hat to confuse a Face ID model. But the paper’s results concern making the wearer less recognizable, not impersonating another person: Section 2.1 (p. 2) distinguishes impersonation from dodging, and the Testing Protocol (p. 5) describes its attacks as dodging attacks. (LLM, conf=0.90)
- Partly supportedcites [73] [73] Mahmood Sharif, Sruti Bhagavatula, Lujo Bauer, and Michael K Reiter. A general framework for adversarial examples with objectives. ACM Transactions on Privacy and Security (TOPS) , 22(3):1-30, 2019. - sourceExperimental — accuracy not yet measured
The Introduction and Experiment Setup (pages unavailable in our copy) describe impersonation attacks against face-recognition DNNs using printed adversarial patterns affixed to eyeglasses worn by attackers. The source does not establish that face-recognition systems generally are easily spoofed by a small patch: it tests particular DNNs and eyeglass-based attacks under controlled conditions, and notes that some physical impersonation attempts failed. (LLM, conf=0.84)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Some pre-trained models are reported to output training text data containing private user information such as addresses [63].”
What the sources say
- Could not verifycites [63] [63] Inioluwa Deborah Raji, Andrew Smart, Rebecca N White, Margaret Mitchell, Timnit Gebru, Ben Hutchinson, Jamila Smith-Loud, Daniel Theron, and Parker Barnes. Closing the ai accountability gap: Defining an end-to-end framework for internal algorithmic auditing. In Proceedings of the 2020 conference on fairness, accountability, and transparency , pages 33-44, 2020. - sourceExperimental — accuracy not yet measured
Section 4.4.2 discusses documentation for trained models, and Section 4.6 discusses privacy practices for face data; neither reports a model outputting private information from its training text. Searches for pre-trained models, training-text leakage, and addresses found no passage addressing the claim. The retrieved passages provide section labels but no page numbers. (LLM, conf=0.76)
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
72 more claims · 5 with their cited sources checked
Create a free account to see all 282 claims and to verify the 38 references still open.
- Probably not a substantial claim. 191
- It may state two separate claims as one. 43
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“An effective automated audit system for authorship and provenance compliance functions as a continuous pipeline rather than a retrospective review tool [28].”
From Designing automated audit mechanisms to evaluate compliance of generative AI platforms with federal authorship and ownership disclosure requirements. (2023) · cites this paper as [28]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Reliable provenance begins at the moment content is produced, not after distribution [28].”
From Designing automated audit mechanisms to evaluate compliance of generative AI platforms with federal authorship and ownership disclosure requirements. (2023) · cites this paper as [28]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“This high-level understanding will help optimize trust, as operators will be aware of the capabilities and limitations of the AI systems they work with and know the appropriate settings for use104.”
From Adopting and expanding ethical principles for generative artificial intelligence from military to healthcare (2023) · cites this paper as [104]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“This may be deliberate, to protect brand perception or avoid licensing obligations, or unintentional, especially in creative interfaces that mask algorithmic influence behind seemingly manual controls [28].”
From Designing automated audit mechanisms to evaluate compliance of generative AI platforms with federal authorship and ownership disclosure requirements. (2023) · cites this paper as [28]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 3 Trustworthy AI: A Systematic Approach · p. 13
“the lifecycle of the development of a typical AI product can be partitioned into data preparation, algorithm design, development-deployment, and management [25].”
§ 2.6 Privacy protection · p. 12
“the five main stages of the lifecycle of an AI system, i.e., data preparation, algorithm design, development, deployment, and management.”
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
The Nature of Statistical Learning Theory
Vapnik, V. N. (1995) · doi:10.1007/978-1-4757-2440-0 · Cited by 39,138
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834 · cited 1×
“For example, in computer vision, an established successful paradigm involves pre-training models on a largescale dataset, such as ImageNet, and then fine-tuning them on target tasks with fewer training data [131, 224, 375].”
MethodRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684 · cited 1×
“For example, in computer vision, an established successful paradigm involves pre-training models on a largescale dataset, such as ImageNet, and then fine-tuning them on target tasks with fewer training data [131, 224, 375].”
MethodGrad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
The Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · cited 2×
“This challenge arises from various practical AI tasks [343, 391] in the area of transfer learning [255, 350].”
BackgroundLanguage Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
"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
Research works printed but not linked: 60
- Dalal Al-Azizy, David Millard, Iraklis Symeonidis, Kieron O’Hara, and Nigel Shadbolt. 2015. A literature survey and classifications on data deanonymisation. In Proceedings of the International Conference on Risks and Security of Internet and Systems. Springer, 36–51.
- Dzmitry Bahdanau Kyunghyun Cho and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations (ICLR’15) .
- Joy Buolamwini and Timnit Gebru. 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on Fairness, Accountability and Transparency. PMLR, 77–91.
- 10.5555/3294996.3295155 · doi:10.5555/3294996.3295155
- Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, et al. 2021. Extracting training data from large language models. In Proceedings of the 30th USENIX Security Symposium (USENIX Security’21). 2633–2650.
- Yu Cheng Mo Yu Xiaoxiao Guo and Bowen Zhou. 2019. Few-shot learning with meta metric learners. In NIPS 2017 Workshop on Meta-Learning .
- Moustapha Cisse, Piotr Bojanowski, Edouard Grave, Yann Dauphin, and Nicolas Usunier. 2017. Parseval networks: Improving robustness to adversarial examples. In International Conference on Machine Learning. PMLR, 854–863.
- Bo Cowgill and Catherine Tucker. 2017. Algorithmic bias: A counterfactual perspective. NSF Trustworthy Algorithms.
- Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Edoardo Debenedetti, Nicolas Flammarion, Mung Chiang, Prateek Mittal, and Matthias Hein. 2021. RobustBench: A standardized adversarial robustness benchmark. In Proceedings of the 35th Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).
- Luiz Marcio Cysneiros and Vera Maria Benjamim Werneck. 2009. An initial analysis on how software transparency and trust influence each other. In Proceedings of the Workshop on Requirements Engineering (WER’09). Citeseer.
- Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. 2017. CARLA: An open urban driving simulator. In Conference on Robot Learning. PMLR, 1–16.
- 10.5555/1791834.1791836 · doi:10.5555/1791834.1791836
- Exforsys. 2011. What Is Monkey Testing. Retrieved July 9, 2021 from http://www.exforsys.com/tutorials/testing-types/ monkey-testing.html.
- Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In International Conference on Machine Learning. PMLR, 1126–1135.
- Shixiang Gu and Luca Rigazio. 2015. Towards deep neural network architectures robust to adversarial examples. In 3rd International Conference on Learning Representations (ICLR’15) San Diego CA USA May 7-9 2015 Workshop Track Proceedings .
- IBM. Trusting AI. Retrieved February 20, 2021 from https://www.research.ibm.com/artificial-intellig ence/trusted-ai/.
- Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning. PMLR, 448–456.
- Shouling Ji, Weiqing Li, Prateek Mittal, Xin Hu, and Raheem Beyah. 2015. \(\lbrace\) SecGraph \(\rbrace\) : A uniform and open-source evaluation system for graph data anonymization and de-anonymization. In Proceedings of the 24th USENIX Security Symposium (USENIX Security’15). 303–318.
- Gregory Koch, Richard Zemel, and Ruslan Salakhutdinov. 2015. Siamese neural networks for one-shot image recognition. In ICML Deep Learning Workshop, Vol. 2.
- Pang Wei Koh and Percy Liang. 2017. Understanding black-box predictions via influence functions. In International Conference on Machine Learning. PMLR, 1885–1894.
- Klas Leino, Zifan Wang, and Matt Fredrikson. 2021. Globally-robust neural networks. In International Conference on Machine Learning. PMLR, 6212–6222.
- Ke Li and Jitendra Malik. 2017. Learning to optimize. In International Conference on Learning Representations .
- Yiming Li Yong Jiang Zhifeng Li and Shu-Tao Xia. 2017. Backdoor learning: A survey. IEEE Transactions on Neural Networks and Learning Systems .
- Kang Liu, Brendan Dolan-Gavitt, and Siddharth Garg. 2018. Fine-pruning: Defending against backdooring attacks on deep neural networks. In International Symposium on Research in Attacks, Intrusions, and Defenses. Springer, 273–294.
- Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards deep learning models resistant to adversarial attacks. In International Conference on Learning Representations.
- Pratyush Maini, Eric Wong, and Zico Kolter. 2020. Adversarial robustness against the union of multiple perturbation models. In International Conference on Machine Learning. PMLR, 6640–6650.
- Andre Martins and Ramon Astudillo. 2016. From softmax to sparsemax: A sparse model of attention and multi-label classification. In International Conference on Machine Learning. PMLR, 1614–1623.
- Jan Hendrik Metzen Tim Genewein Volker Fischer and Bastian Bischoff. 2017. On detecting adversarial perturbations. In 5th International Conference on Learning Representations (ICLR’17) Toulon France April 24-26 2017 Conference Track Proceedings .
- Silvio Micali, Oded Goldreich, and Avi Wigderson. 1987. How to play any mental game. In Proceedings of the 19th ACM Symposium on Theory of Computing (STOC’87). ACM, 218–229.
- Christoph Molnar. 2020. Interpretable Machine Learning. Retrieved from Lulu.com.
- OpenAI. 2018. OpenAI Charter. Retrieved February 20, 2021 from https://openai.com/charter/.
- Andrea Paudice, Luis Muñoz-González, and Emil C. Lupu. 2018. Label sanitization against label flipping poisoning attacks. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 5–15.
- Aditi Raghunathan, Jacob Steinhardt, and Percy Liang. 2018. Certified defenses against adversarial examples. In Proceedings of the International Conference on Learning Representations.
- Aditi Raghunathan Sang Michael Xie Fanny Yang John C. Duchi and Percy Liang. 2019. Adversarial training can hurt generalization. In ICML 2019 Workshop Deep Phenomena .
- Yuji Roh, Kangwook Lee, Steven Whang, and Changho Suh. 2020. FR-train: A mutual information-based approach to fair and robust training. In International Conference on Machine Learning. PMLR, 8147–8157.
- Christian Sandvig, Kevin Hamilton, Karrie Karahalios, and Cedric Langbort. 2014. Auditing algorithms: Research methods for detecting discrimination on internet platforms. In Proceedings of the Data and Discrimination: Converting Critical Concerns Into Productive Inquiry 22 (2014), 4349–4357.
- Adam Santoro, Sergey Bartunov, Matthew Botvinick, Daan Wierstra, and Timothy Lillicrap. 2016. Meta-learning with memory-augmented neural networks. In International Conference on Machine Learning. PMLR, 1842–1850.
- Sebastian Schelter, Joos-Hendrik Boese, Johannes Kirschnick, Thoralf Klein, and Stephan Seufert. 2017. Automatically tracking metadata and provenance of machine learning experiments. In Machine Learning Systems Workshop at NIPS. 27–29.
- Avanti Shrikumar, Peyton Greenside, and Anshul Kundaje. 2017. Learning important features through propagating activation differences. In International Conference on Machine Learning. PMLR, 3145–3153.
- Simone Stumpf, Adrian Bussone, and Dympna O’sullivan. 2016. Explanations considered harmful? user interactions with machine learning systems. In Proceedings of the ACM SIGCHI Conference on Human Factors in Computing Systems (CHI).
- Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai. 2019. VL-BERT: Pre-training of generic visual-linguistic representations. In Proceedings of the International Conference on Learning Representations.
- Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International Conference on Machine Learning. PMLR, 3319–3328.
- Supreme Audit Institutions of Finland, Germany, the Netherlands, Norway and the UK. 2020. Auditing Machine Learning Algorithms. Retrieved from https://www.auditingalgorithms.net/index.html.
- Liang Tong, Bo Li, Chen Hajaj, Chaowei Xiao, Ning Zhang, and Yevgeniy Vorobeychik. 2019. Improving robustness of \(\lbrace\) ML \(\rbrace\) classifiers against realizable evasion attacks using conserved features. In Proceedings of the 28th USENIX Security Symposium (USENIX Security’19). 285–302.
- Cecília Torres, Walter Franklin, and Laura Martins. 2018. Accessibility in chatbots: The state of the art in favor of users with visual impairment. In International Conference on Applied Human Factors and Ergonomics. Springer, 623–635.
- Florian Tramèr, Alexey Kurakin, Nicolas Papernot, Ian Goodfellow, Dan Boneh, and Patrick McDaniel. 2018. Ensemble adversarial training: Attacks and defenses. In Proceedings of the International Conference on Learning Representations.
- Florian Tramèr, Fan Zhang, Ari Juels, Michael K. Reiter, and Thomas Ristenpart. 2016. Stealing machine learning models via prediction \(\lbrace\) APIs \(\rbrace\) . In Proceedings of the 25th USENIX Security Symposium (USENIX Security’16). 601–618.
- Dimitris Tsipras Shibani Santurkar Logan Engstrom Alexander Turner and Aleksander Ma̧dry. 2019. Robustness may be at odds with accuracy. In 7th International Conference on Learning Representations (ICLR’19) New Orleans LA USA May 6-9 2019 .
- UNI Global Union. 2017. Top 10 principles for ethical artificial intelligence. In The Future World of Work.
- Yisen Wang, Xingjun Ma, James Bailey, Jinfeng Yi, Bowen Zhou, and Quanquan Gu. 2019. On the convergence and robustness of adversarial training. In Proceedings of the International Conference on Machine Learning (ICML’19), Vol. 1. 2.
- Yingxu Wang and Jingqiu Shao. 2003. Measurement of the cognitive functional complexity of software. In Proceedings of the 2nd IEEE International Conference on Cognitive Informatics. IEEE, 67–74.
- Tsui-Wei Weng, Huan Zhang, Pin-Yu Chen, Jinfeng Yi, Dong Su, Yupeng Gao, Cho-Jui Hsieh, and Luca Daniel. 2018. Evaluating the robustness of neural networks: An extreme value theory approach. In Proceedings of the International Conference on Learning Representations.
- Tong Wu Liang Tong and Yevgeniy Vorobeychik. 2020. Defending against physically realizable attacks on image classification. In 8th International Conference on Learning Representations (ICLR’20) Addis Ababa Ethiopia April 26-30 2020 .
- Weiyi Xia, Yongtai Liu, Zhiyu Wan, Yevgeniy Vorobeychik, Murat Kantacioglu, Steve Nyemba, Ellen Wright Clayton, and Bradley A. Malin. 2021. Enabling realistic health data re-identification risk assessment through adversarial modeling. J. Am. Med. Inf. Assoc. 28, 4 (2021), 744–752.
- Han Xu, Xiaorui Liu, Yaxin Li, Anil Jain, and Jiliang Tang. 2021. To be robust or to be fair: Towards fairness in adversarial training. In International Conference on Machine Learning. PMLR, 11492–11501.
- Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International Conference on Machine Learning. PMLR, 2048–2057.
- 10.5555/1382436.1382751 · doi:10.5555/1382436.1382751
- Ting Yao, Yiheng Zhang, Zhaofan Qiu, Yingwei Pan, and Tao Mei. 2021. Seco: Exploring sequence supervision for unsupervised representation learning. In AAAI, Vol. 2. 7.
- Matei Zaharia, Andrew Chen, Aaron Davidson, Ali Ghodsi, Sue Ann Hong, Andy Konwinski, Siddharth Murching, Tomas Nykodym, Paul Ogilvie, Mani Parkhe, et al. 2018. Accelerating the machine learning lifecycle with MLflow. IEEE Data Eng. Bull. 41, 4 (2018), 39–45.
- Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, and Cynthia Dwork. 2013. Learning fair representations. In International Conference on Machine Learning. PMLR, 325–333.
Cited by
Items 301–400 of 576
Bohoran, T. A., Kampaktsis, P. Ν., McLaughlin, L., Leb, J. S., Moustakidis, S., McCann, G. P., & Giannakidis, A. (2024) · International Conference on Machine Vision · doi:10.1117/12.3023433 · Cited by 2
“This work aligns with trustworthy artificial intelligence [17] since it can be used to enhance the decision-making process and reduce risks.”
MethodHow Trueness of Clinical Decision Support Systems Based on Machine Learning Is Assessed?
Poiron, A., Cabon, S., & Marc Cuggia, A. (2024) · Studies in health technology and informatics · doi:10.3233/shti240535 · Cited by 2
Ma, J., Zhou, Y., He, L., Liu, X., Zheng, Y., & Hong, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5340689 · Cited by 6
Human Intelligence vs. Artificial Intelligence
Liu, P., & Yu, D. (2026) · Wiley eBooks · doi:10.1002/9781394266401.ch5 · Cited by 3
Verification of Deep Neural Networks with KGZ-Based zkSNARK
Thakur, S., & Breslin, J. G. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-66336-9_6 · Cited by 1
BalancedSecAgg: Toward Fast Secure Aggregation for Federated Learning
Masuda, H., Kita, K., Koizumi, Y., Takemasa, J., & Hasegawa, T. (2024) · IEEE Access · doi:10.1109/access.2024.3491779 · Cited by 1
Handling Veracity of SVM Predictions
Loor, M., Tapia-Rosero, A., & Tré, G. D. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-74003-9_5 · Cited by 2
Liu, Y., Awang, H., & Mansor, N. S. (2024) · International Conference on Network Applications, Protocols and Services (NETAPPS) · doi:10.1109/netapps63333.2024.10823621 · Cited by 2
“The swift advancement of AI continues to yield substantial economic and social advantages, which has extensively influenced numerous domains including transportation, economics, medicine, security and recreation [2].”
Designing Trustworthy AI in Higher Education
Rebholz, S., Libbrecht, P., & Müller, W. (2025) · Artificial intelligence · doi:10.5772/intechopen.1009134 · Cited by 1
Explore the Hallucination on Low-level Perception for MLLMs
Sun, Y., Zhang, Z., Wu, H., Liu, X., Lin, W., Zhai, G., & Min, X. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888437 · Cited by 6
“Despite their impressive vision-language understanding capabilities, MLLMs are still not considered trustworthy AI systems [5].”
BackgroundCertified unlearning for a trustworthy machine learning-based access control administration
Llamas, J. M., Preuveneers, D., & Joosen, W. (2025) · International Journal of Information Security · doi:10.1007/s10207-025-01003-5 · Cited by 2
Uncertainty-Aware Stability Analysis of IBR-Dominated Power System With Neural Networks
Humblot-Renaux, G., Wu, Y., Escalera, S., et al. (2025) · IEEE Transactions on Power Electronics · doi:10.1109/tpel.2025.3560236 · Cited by 1
“However, thecriticaldisadvantageofML-basedstabilityanalysisisthat itcannotguarantee100%stabilitypredictionaccuracy[8].”
Xue, C., Gao, J., & Gu, Z. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3574299 · Cited by 2
“All these methods fall under the framework of trustworthy machine learning [7], where “trustworthiness” generally encompasses four key metrics: the model’s ability to generalize, its robustness (security), interpretability, and fairness [8].”
Evaluation of Post-Hoc Explainability Methods for Glaucoma Classification Using Fundus Images
Ming, H. K., Vong, W.-T., Loh, B. C. S., & Then, P. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-92605-1_40 · Cited by 1
Constant-Round Privacy-Preserving KNN Classification Based on Function Secret Sharing
Liu, B., Yang, X., & Tang, X. (2026) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2026.3689015 · Cited by 1
Self-citationInfluencing the Perception and Acceptance of AI-Generated Marketing Content as Part of SGD
Kubovics, M. (2025) · Journal of Lifestyle and SDGs Review · doi:10.47172/2965-730x.sdgsreview.v5.n06.pe06929 · Cited by 2
Philps, B., Hernández, M. D. C. V., Qin, C., Clancy, Ú., Sakka, E., Maniega, S. M., Bastin, M. E., Jochems, A. C. C., Wardlaw, J. M., & Bernabéu, M. O. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103697 · Cited by 6
Defining dangerous AI: existential risk, power-intelligence, and the limits of AGI
Sass, R. (2025) · AI and Ethics · doi:10.1007/s43681-025-00790-w · Cited by 6
When engineering meets economics: AI-powered safe and accountable autonomous driving
Di, X. S., Dawid, H., & Muehlheusser, G. (2025) · Artificial Intelligence for Transportation · doi:10.1016/j.ait.2025.100020 · Cited by 2
Sullivan, B., Svendsen, S., & Khan, J. A. (2025) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2025-spring65109.2025.11174467 · Cited by 1
“However, existing FL-based trust models [10] do not scale well due to their high computation and communication overhead.”
Al-Smadi, R. W. (2025) · Human Behavior and Emerging Technologies · doi:10.1155/hbe2/6067964 · Cited by 3
Be Reliable: An Interpretable Attribute-Oriented Representation Learning Framework
Fang, Z., Du, S., Zou, Y., Tan, Y., Song, N., & Wang, S. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3618290 · Cited by 9
“We can categorize model interpretability into two primary types: empirical-and design-level interpretability [25], [26].”
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
“Addressing these challenges and various aspects of engineering trustworthy systems [3] requires different methods for designing machine learning and artificial intelligence systems, combining formal mathematical modeling, data-driven engineering methods, and long-term risk analysis [4–6].”
Subject-Specific Scalar-on-Image Regression
Liu, L. Y.-F., Ma, H., Liu, Y., & Hongtu Zhu, B. (2025) · Journal of Data Science · doi:10.6339/25-jds1203 · Cited by 1
Fail‐Controlled Classifiers: A Swiss‐Army Knife Toward Trustworthy Systems
Khokhar, F. A., Zoppi, T., Ceccarelli, A., Montecchi, L., & Bondavalli, A. (2025) · Software Practice and Experience · doi:10.1002/spe.70033 · Cited by 2
“Therefore, there is no need to strive for very specific solutions that aim at maximizing the accuracy [52, 53], which are exceedingly common when dealing with ML-based software.”
Public Perception of Accountability for AI Systems: The Influence of Age and Education
Ng, S. Y., Crockett, K. A., Latham, A., & Kaleem, M. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227931 · Cited by 2
On the Volatility of Shapley-Based Contribution Metrics in Federated Learning
Geimer, A., Pontiveros, B. B. F., & State, R. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228157 · Cited by 3
“Robustness, fairness, and generalization as parts of trust-worthiness have become an important aspect of Artificial Intelligence [33].”
An investigation of visual foundation models robustness
Gupta, S. K., & Passerone, R. (2025) · Machine Learning · doi:10.1007/s10994-025-06853-7 · Cited by 4
“Ideally, the robustness of a network can be specified as its ability to generalize to new and unseen data and be resistant to transformations, noise, errors, and adversarial attacks [41].”
Understanding Neurocognition With Deep Learning and MRI: A Systematic Review
Rahman, M. T., Orka, N. A., Khan, A., Lió, P., & Moni, M. A. (2025) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2025.3635161 · Cited by 7
“Trustworthy AI deployment depends on regulatory frameworks that ensure accountability, fairness, and transparency [112].”
A Brief History of Formal Methods in China
Zhan, N., Woodcock, J., Wang, J., & Chen, M. (2025) · Formal Aspects of Computing · doi:10.1145/3783996 · Cited by 1
“Notably, many of these considerations extend beyond China and are relevant to the global FM community.”
Zhang, L., Jia, Y., & Wu, Q. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.115139 · Cited by 1
PDFL: A Privacy-Enhancing and Robust Poisoning Defense Federated Learning Scheme
Wang, G., Wu, H., Li, Q., Liu, Z., Zhao, J., Lam, K., Dong, Q., Yang, Y., & Zhou, L. J. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3648147 · Cited by 1
Counterfactual Explanation-Based Cryptocurrency Price Prediction
Luo, X., & Yin, W. (2026) · Entropy · doi:10.3390/e28010065 · Cited by 2
“In the high-stakes domain of cryptocurrency trading and risk management, this “black-box” nature directly undermines trustworthiness [14,15].”
Neurosymbolic AI for Enhanced Reasoning in Small Language Models
Sidhu, M. S., Kapoor, N., Batra, N., Juwairiyyah, J., & Firdouse, F. (2025) · International Symposium on Advanced Electrical and Communication Technologies (ISAECT) · doi:10.1109/isaect68904.2025.11318815 · Cited by 1
“Graphs, such as a reasoning graph, attention heatmap, and an efficiency plot, are in line with the current AI evaluation practices [4].”
InfluentialQin, Z., Lu, K., Liu, Y., Chen, L., & Song, Y. (2026) · Computers & Security · doi:10.1016/j.cose.2026.104867 · Cited by 1
Audit-as-code: a policy-as-code framework for continuous AI assurance
Muhammad, A. E., Yow, K., & Alsenan, S. A. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1759211 · Cited by 13
Evolution of AI Agent Registry Solutions: Centralized, Enterprise, and Distributed Approaches
Singh, A., Ehtesham, A., Lambe, M., Grogan, J., Singh, A., Kumar, S., Muscariello, L., Pandey, V., Marc, G. S. D. S., Chari, P., et al. (2025) · IEEE International Conference on Cognitive Machine Intelligence (CogMI) · doi:10.1109/cogmi67134.2025.00067 · Cited by 15
“Traditional mechanisms like DNS and static service catalogs are poorly suited to agent ecosystems, which demand dynamic discovery , verifiable metadata , and privacy-preserving interactions [1].”
A GeoAI-Driven and Decision-Oriented Methodology for Multi-Hazard Early Warning System Development
Lu, Q., Wen, J., Yan, J., Wang, Y., & Hao, C. (2026) · International Journal of Disaster Risk Science · doi:10.1007/s13753-026-00715-z · Cited by 4
Learning Class Similarities for Enhanced Image Out-Of-Distribution Detection
Spanos, D., Passalis, N., & Tefas, A. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460728 · Cited by 1
How trustworthy AI fosters adoption and user advocacy in financial advisory services
Sungkarungsri, P., & Kiattisin, S. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01451-5 · Cited by 5
“It reflects how individuals evaluate an AI system’s reliability, rather than being an inherent attribute of the technology [30, 32].”
InfluentialUntrustVul: Automated Untrustworthy Alert Identification in Vulnerability Detection Models
Tung, L. N., Du, X., Neelofar, N., & Aleti, A. (2026) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2026.3693636 · Cited by 1
“Trustworthiness is a complex concept, making it challenging for researchers to agree on a unified definition [22], [23].”
Nasichah, I. M., Irawan, M. I., & Setiyono, B. (2026) · Array · doi:10.1016/j.array.2026.100907 · Cited by 1
Drzyzga, G., & Janneck, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30846-7_17 · Cited by 1
Wang, Y., Guo, S., Wang, Z., & Chen, X. (2026) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2026.117255 · Cited by 2
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
“These approaches are important for transitioning from theory to the practical implementation of reliable AI in the form of standards, best practices, and widely accepted requirements that developers should follow [9].”
InfluentialManziuk, E. (2022) · Computer Systems and Information Technologies · doi:10.31891/csit-2022-1-11 · Cited by 2
Disruptive AI Technology and Hate Speech: A Legal Redress in Malaysia
Saufi, N. N. M., Kamaruddin, S., Mohammad, A. M., Jabar, N. A. B. A., Rosli, W. R. W., & Talib, Z. M. (2023) · International Conference on Disruptive Technologies (ICDT) · doi:10.1109/icdt57929.2023.10150942 · Cited by 3
“[30] .”
Mitigating Robustness Bias: Theoretical Results and Empirical Evidences
Franco, D., Oneto, L., & Anguita, D. (2023) · European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) · doi:10.14428/esann/2023.es2023-30 · Cited by 2
“Nevertheless, these achievements are accompanied by increasing concerns about their impacts on society [4].”
BackgroundU-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
Human-AI Engineering for Adults
Meyer-Vitali, A., & Mulder, W. (2024) · Frontiers in artificial intelligence and applications · doi:10.3233/faia240197 · Cited by 1
Responsible Artificial Intelligence Systems: From Trustworthiness to Governance
Herrera, F. (2024) · Design, Automation, and Test in Europe · doi:10.23919/date58400.2024.10546553 · Cited by 2
Introduction to Explainable AI: Unveiling the Black Box
Mittal, D., Parashar, A. R., & Singh, P. K. (2024) · Advances in environmental engineering and green technologies book series · doi:10.4018/979-8-3693-7822-9.ch006 · Cited by 1
MURDOC: Transforming Pixels into Perception for Camouflage Detection
Hogue, D., Kastl, Z., Karch, J., Nguyen, D., Schley, L., Lewis, J., Connelly, S., & Weaver, C. (2024) · IEEE/AIAA Digital Avionics Systems Conference (DASC) · doi:10.1109/dasc62030.2024.10748781 · Cited by 1
“Understanding and trusting AI systems’ decision-making processes is essential for fostering user confidence, ensuring accountability, and facilitating meaningful collaboration between humans and machines [1]–[4].”
Benchmarking with a Language Model Initial Selection for Text Classification Tasks
Riyadi, A., Kovacs, M., Serdült, U., & Kryssanov, V. V. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7010003 · Cited by 2
Kabir, M. A., Islam, M. M. M., Chakraborty, N. R., & Noori, S. R. H. (2025) · Springer series in advanced manufacturing · doi:10.1007/978-3-031-80154-9_9 · Cited by 4
Zhang, X., Zhou, W., Hu, W., Zhou, S., Hu, X., & Yang, L. (2025) · Technology in Society · doi:10.1016/j.techsoc.2025.102900 · Cited by 1
Yang, J. L., Yang, X., Lyu, M., & Zhang, J. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3571134 · Cited by 6
“Moreover, European Union has explicitly stated that AI must be human-centered [5], emphasizing interaction between technology and humans to facilitate better development and updates [6].”
On the Need for Trustworthy Deep Learning Models for Efficient Resource Management in 6G Networks
Keramidi, I. P., Lakoumentas, J., Zervou, P., Ramantas, K., Vardakas, J. S., & Verikoukis, C. V. (2025) · International Conference on Communications · doi:10.1109/icc52391.2025.11162101 · Cited by 1
“Trustworthy AI has been typically associated with explain-able models (or XAI) and Bayesian Neural Networks [5]; however the development of non-Bayesian trustworthy DL models has recently gained ground in the academia since they are less complex methods [6].”
Walk the Talk: Is Your Log-based Software Reliability Maintenance System Really Reliable?
He, M., Jia, T., Duan, C., Xiao, P., Zhang, L., Wang, K., Wu, Y., Li, Y., & Huang, G. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00316 · Cited by 12
“Specifically, these deep learning-based anomaly detection systems function as black boxes to service providers utilizing them [26]–[28], allowing providers only to obtain detection results without understanding how anomalies are detected, or whether the results are trustworthy.”
Developing an ethical framework for intelligence-AI
Bellaby, R. W. (2026) · AI and Ethics · doi:10.1007/s43681-026-01076-5 · Cited by 1
A Semantically Informed Benchmark Dataset for Computer Vision in Aviation Systems
Reynolds, S., & Ochoa, O. (2023) · IEEE/AIAA Digital Avionics Systems Conference (DASC) · doi:10.1109/dasc58513.2023.10311196 · Cited by 1
“In other works, there are several technical and ethical requirements that contribute to trustworthiness in AI [17].”
BackgroundInfluentialA Scoping Review On The Impact Of Algorithm Bias On The Perceived FairnessPreprint
Saryazdi, A. H., & Mirhoseini, M. (2023) · Research Square · doi:10.21203/rs.3.rs-3428999/v1 · Cited by 2
Alelyani, T. (2024) · Research Square · doi:10.21203/rs.3.rs-3741717/v1 · Cited by 1
Schmidt, J. B., Nielsen, K. L., Strunin, D., Kirkby, N., Thomassen, J., Rasmussen, S. C., Frikke-Schmidt, R., Hertz, F., & Engsig-Karup, A. (2025) · medRxiv · doi:10.1101/2025.01.21.25320878 · Cited by 1
Adversarial Attacks on Machine Learning-Driven High-Frequency Trading ModelsPreprint
Shimao, H., Saengchote, K., Chakraborty, K., Wang, C., & Khern-am-nuai, W. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5367043 · Cited by 1
Responsible Use of AI in Healthcare
Gupta, S. (2026) · doi:10.1002/9781394355471.ch13 · Cited by 1
Dissecting deep models: removal and zeroing-based explanation (RZE) techniques
Ziweritin, S., Gunasekaran, A., Iram, S., & Chen, M. (2026) · Evolving Systems · doi:10.1007/s12530-026-09840-y · Cited by 2
A Framework for Global Trust and Reputation Management in 6G Networks
Trinh-Nguyen, B., Berri, S., Teo, S. G., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-00552-6_4 · Cited by 1
Vladika, J., Domres, A., Nguyen, M., Moser, R., Nano, J., Busch, F., Adams, L. C., Bressem, K. K., Bernhardt, D., Combs, S. E., et al. (2025) · arXiv · doi:10.48550/arxiv.2505.24830 · Cited by 1
Towards determining the criticality of AI applications: A model risk management perspective
Sateli, B., Castillo, F. D., & Moshtagi, R. (2023) · doi:10.21428/594757db.74665221 · Cited by 1
Towards Machine Learning Models that We Can Trust: Testing, Improving, and Explaining Robustness
Pintor, M., Demontis, A., & Biggio, B. (2023) · European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) · doi:10.14428/esann/2023.es2023-5
“Fairness emphasizes the equitable treatment of different groups and demographics, guarding against biased outcomes and social discrimination [4].”
BackgroundToward Responsible Artificial Intelligence Systems: Safety and Trustworthiness
Herrera, F. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-49252-5_2 · Cited by 1
“It should be noted that the adoption of trustworthy AI [7, 8] in the form of practical frameworks is not yet a reality.”
BackgroundOn the compliance with ethical principles in AI
Danilevskyi, M., & Tellez, F. P. (2023) · doi:10.1145/3633083.3633223
Where has privacy gone?Preprint
Aïmeur, E., & Brassard, G. (2024) · doi:10.22541/au.170664083.33427025/v1
Toward Trustworthiness of Deep Learning Models for 12-Lead ECGs
Bender, T. (2024) · eDiss (Georg-August-Universität Göttingen) · doi:10.53846/goediss-10315
Flex: Flexible Federated Learning FrameworkPreprint
Herrera, F., Jiménez-López, D., Argente-Garrido, A., Rodríguez-Barroso, N., Zuheros, C., Aguilera, I., Bello, B., García-Márquez, M., & Luzón, M. V. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4764504
Wae: An Evaluation Metric for Attribution-Based Xai on Time Series ForecastingPreprint
Chen, Y., & Zhang, S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4769820
Kou, T. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4806609
Marwala, T., & Mpedi, L. G. (2024) · Springer eBooks · doi:10.1007/978-981-97-2827-5_12
Trustworthy AI: Deciding What to Decide
Wu, C., Li, Y.-F., Li, J., Xu, J., & Bouvry, P. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-62281-6_8 · Cited by 6
González, M. J., & Rodríguez, A. L. T. (2024) · Enrahonar An international journal of theoretical and practical reason · doi:10.5565/rev/enrahonar.1575 · Cited by 1
SLM-AIE: A Systematic Literature Map of Artificial Intelligence EthicsPreprint
Atlam, E., Almaliki, M., Alfahaid, A., Gad, I., Elmarhomy, G., Alwateer, M. M., & Ahmed, A. (2024) · Research Square · doi:10.21203/rs.3.rs-4723233/v1 · Cited by 2
Efficient Deep Neural Network Verification with QAP-Based ZkSNARK
Thakur, S., & Breslin, J. G. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-66705-3_12
Kemmerzell, N., & Schreiner, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70893-0_10 · Cited by 5
Schork, S., & Rötzel, P. G. (2024) · Springer eBooks · doi:10.1007/978-3-658-43816-6_1
Guest Editorial: Trustworthy Machine Learning for Health Informatics
Luo, L., Xu, D., Qin, J., Jin, Y., & Chen, H. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3472368
A Method to Evaluate the Credibility of Domain Knowledge Network Using Validated Expert Knowledge
Li, Y., Zhou, Y., Liao, L., et al. (2024) · International Journal of Software Engineering and Knowledge Engineering · doi:10.1142/s0218194025500020
Self-citationAn Approach to Associate Provenance From ML Pipelines With Transparency and Accountability
Targino, N., Souza, D., & Salgado, A. C. (2024) · International Conference on Information, Intelligence, Systems & Applications (IISA) · doi:10.1109/iisa62523.2024.10786622 · Cited by 1
Explainable and Trustworthy AI with Neuro-Symbolic Approaches
Bhuyan, B. P., Ramdane-Chérif, A., Singh, T. P., & Tomar, R. (2024) · Studies in computational intelligence · doi:10.1007/978-981-97-8171-3_16
Challenges as a framework for trustworthy AI
Antonelli, M., Farahani, K., Sudre, C. H., Cardoso, M. J., Maier‐Hein, L., & Reinke, A. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-323761-4.00020-1
CE:Knowledge Tracking Model Uncertainty Assessment Method Under Trusted Artificial Intelligence
Bai, J., Kang, B., Hu, K., Zheng, Q., & Wang, X. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10831813
“LI, QI, et al. provided a comprehensive review on building trustworthy A comprehensive guide to AI systems [29], emphasizing theoretical frameworks for trustworthy aspects of AI , such as interpretability, and providing concrete recommendations for action.”
Evaluating Legal Compliance of Federated Learning Tools for the European Health Data Space (EHDS)
Gonçalves, S., Lucas, R., Viana, R., Lopes, T., Portugal, A., Morais, M. G. G., & Fernández, M. (2024) · International Conference on Federated Learning Technologies and Applications (FLTA) · doi:10.1109/flta63145.2024.10839840 · Cited by 2
“Li et al. [15] explore the principles necessary to establish and maintain trust in artificial intelligence (AI) systems, focusing especially on ethical principles such as fairness, trans-parency, privacy, and security.”
InfluentialKılıç, D. K., Nielsen, P. A., Miehe, F., & Yafrani, M. E. (2025) · International Journal of Systems Science · doi:10.1080/00207721.2025.2455998 · Cited by 1
“The development of guidelines, methodologies, and best practices that contribute to the trustworthiness of the application is instructed in Li et al. (2023).”
InfluentialUm Processo para Elicitar Requisitos Confiáveis em Sistemas de Aprendizado de Máquina
da Silva, F. L. Q., Sampaio, A. L., Bezerra, C. I. M., & Monteiro, I. T. (2025) · iSys - Brazilian Journal of Information Systems · doi:10.5753/isys.2025.3878 · Cited by 1
Prototypical Part Transformer for Interpretable Image Recognition
Yu, A., & Yang, Y.-B. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890753
“Prototypical learning approaches learn a mapping from the input data into a metric or semi-metric space, where similarity scores are computed by comparing the output features of a feature extractor and the learned prototypical representations [1].”
Tmrf: Trustworthy microstructure recognition framework with deep learning and explainable AI
Pratap, A., Hsiung, P., & Sardana, N. (2025) · Journal of materials research/Pratt's guide to venture capital sources · doi:10.1557/s43578-025-01548-0
Fabris, V. L., de Oliveira, J. R., Silva, C. H. B., Cassenote, V., da Silva, J. V. N. A., Arrais, R. R., & Paris, R. D. (2024) · doi:10.5753/eniac.2024.245025
KAIM: A distributed K-anonymity selection mechanism based on dual incentives
Hu, Z., Ni, S., Quan, H., et al. (2025) · Ad Hoc Networks · doi:10.1016/j.adhoc.2025.103839
A Trusted Measurement Model of AI Algorithm for Power Grid Scheduling in Predictive Scenarios
Wang, Z., Ren, H., Han, Z., Chen, H., Liu, Y., Hu, Y., & Gao, F. (2025) · International Conference on Electrical Automation and Artificial Intelligence (ICEAAI) · doi:10.1109/iceaai64185.2025.10956436
“These AI algorithms, through the analysis and processing of vast amounts of data, can provide more accurate predictions and optimization solutions for grid dispatching, thereby improving the efficiency and reliability of grid operations [1] [2].”
Ohliger, U. A., Winter, J., von Richthofen, G., Gümüşay, A. A., & Hünsche, M. (2025) · Globale Ziele für nachhaltige Entwicklung. · doi:10.1007/978-3-662-68327-9_1-1
Metadata
- Authors
- Li, B., Qi, P., Liu, B., Di, S., Liu, J., Pei, J., Yi, J., & Zhou, B.
- Affiliations
- Tsinghua University (CN)
- Amazon (United States) (US)
- Walmart Inc., Mountain View, CA, USA
- Jingdong (China) (CN)
- JD Technology, Mountain View, CA, USA
- Frontis.AI, Beijing, China
- Venue
- ACM Computing Surveys
- Published
- 2023-01-16
- Volume
- 55
- Issue
- 9
- Pages
- 1-46
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W3202183072
- Cited by
- 612
- References
- 384
- Citations by year
- 2026: 164 · 2025: 207 · 2024: 169 · 2023: 65
- FWCI
- 129.72
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Computing Surveys (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- 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
- trustworthy AI, robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, accountability, AI lifecycle, AI governance, continuous monitoring, algorithmic bias, imperceptible attacks
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-29, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-29 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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.