Blockchain for explainable and trustworthy artificial intelligence
The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
The increasing computational power and proliferation of big data are now empowering Artificial Intelligence (AI) to achieve massive adoption and applicability in many fields. The lack of explanation when it comes to the decisions made by today's AI algorithms is a major drawback in critical decision‐making systems. For example, deep learning does not offer control or reasoning over its internal processes or outputs. More importantly, current black‐box AI implementations are subject to bias and adversarial attacks that may poison the learning or the inference processes. Explainable AI (XAI) is a new trend of AI algorithms that provide explanations of their AI decisions. In this paper, we propose a framework for achieving a more trustworthy and XAI by leveraging features of blockchain, smart contracts, trusted oracles, and decentralized storage. We specify a framework for complex AI systems in which the decision outcomes are reached based on decentralized consensuses of multiple AI and XAI predictors. The paper discusses how our proposed framework can be utilized in key application areas with practical use cases. This article is categorized under: Technologies > Machine Learning Technologies > Computer Architectures for Data Mining Fundamental Concepts of Data and Knowledge > Key Design Issues in Data Mining
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.
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
Intriguing 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
Adversarial examples in the physical world
Kurakin, A., Goodfellow, I. J., & Bengio, S. (2018) · Artificial Intelligence Safety and Security · doi:10.1201/9781351251389-8 · Cited by 5,375
The Limitations of Deep Learning in Adversarial Settings
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z. B., & Swami, A. (2016) · 2016 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2016.36 · Cited by 3,993
Practical Black-Box Attacks against Machine Learning
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z. B., & Swami, A. (2017) · Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security · doi:10.1145/3052973.3053009 · Cited by 3,495
One Pixel Attack for Fooling Deep Neural Networks
Su, J., Vargas, D. V., & Sakurai, K. (2019) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2019.2890858 · Cited by 2,406
Explaining prediction models and individual predictions with feature contributions
Štrumbelj, E., & Kononenko, I. (2014) · Knowledge and Information Systems · doi:10.1007/s10115-013-0679-x · Cited by 2,286 · cited 1×
“An interesting idea is to consider that features are players in a coalition game, the prediction value as the total reward of this game and to represent the individual feature contribution by its Shapley value (Strumbelj & Kononenko, 2014).”
BackgroundAwad, E., Dsouza, S., Kim, R., Schulz, J., Henrich, J., Shariff, A., Bonnefon, J.-F., & Rahwan, I. (2018) · Nature · doi:10.1038/s41586-018-0637-6 · Cited by 1,859
Counterfactual explanations without opening the black box: automated decisions and the GDPR
Wachter, S., Mittelstadt, B., & Russell, C. (2017) · SSRN Electronic Journal · doi:10.2139/ssrn.3063289 · Cited by 1,061
Blockchain for AI: review and open research challenges
Salah, K., Rehman, M. H. U., Nizamuddin, N., & Al-Fuqaha, A. (2019) · IEEE Access · doi:10.1109/access.2018.2890507 · Cited by 1,001 · cited 2×
“Considering the scope of this article, we will limit this discussion in this paper and we will urge the interested readers to follow (Salah et al., 2019) for further understanding.”
BackgroundSelf-citationDatta, A., Sen, S., & Zick, Y. (2016) · 2016 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2016.42 · Cited by 728 · cited 1×
“Actual metrics for feature importance and feature interaction were also investigated (Datta, Sen, & Zick, 2016).”
Model-Agnostic Interpretability of Machine Learning
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · arXiv · doi:10.48550/arxiv.1606.05386 · Cited by 699
Brown, T. B., Mané, D., Roy, A., Abadi, M., & Gilmer, J. (2017) · arXiv · doi:10.48550/arxiv.1712.09665 · Cited by 509 · cited 1×
“An adversarial printable patch that can be stuck next to objects was also designed by researchers (Brown, Mane, Roy, Abadi, & Gilmer, 2017).”
BackgroundCombating Deepfake Videos Using Blockchain and Smart Contracts
Hasan, H. R., & Salah, K. (2019) · IEEE Access · doi:10.1109/access.2019.2905689 · Cited by 339 · cited 1×
“Nevertheless, technical AI and XAI trustworthiness enables the implementation of moral and philosophical algorithms, that is, algorithms that are based on ethical principles and philosophical solutions of the so-called “ trolley problems ” (Keeling, 2019).”
BackgroundSelf-citationPerturbation-Based Explanations of Prediction Models
Robnik-Šikonja, M., & Bohanec, M. (2018) · Human–Computer Interaction Series · doi:10.1007/978-3-319-90403-0_9 · Cited by 171 · cited 1×
“The interpretation methods can also be divided into two main approaches: gradient-based approaches which are specific to neural networks, and more general, model-agnostic approaches based on local perturbations and counter-factual examples (Robnik-Sikonja & Bohanec, 2018).”
MethodDignum, V. (2017) · arXiv · doi:10.48550/arxiv.1706.02513 · Cited by 103
Cited by
A survey of blockchain consensus algorithms performance evaluation criteria
Bamakan, S. M. H., Motavali, A., & Babaei Bondarti, A. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113385 · Cited by 481
A Review of Trustworthy and Explainable Artificial Intelligence (XAI)
Chamola, V., Hassija, V., Sulthana, A. R., Ghosh, D., Dhingra, D., & Sikdar, B. (2023) · IEEE Access · doi:10.1109/access.2023.3294569 · Cited by 352
“Local models expressed as a sequential function of input variables can be more efficient than model simulations because limited segments of the system are more inclined to be continuous [52], [55].”
BackgroundTrustworthy Blockchain Oracles: Review, Comparison, and Open Research Challenges
Al-Breiki, H., Rehman, M. H. U., Salah, K., & Svetinovic, D. (2020) · IEEE Access · doi:10.1109/access.2020.2992698 · Cited by 336
Self-citationTsolakis, N., Schumacher, R., Dora, M., & Kumar, M. (2023) · Annals of Operations Research · doi:10.1007/s10479-022-04785-2 · Cited by 325
Nazar, M., Alam, M. M., Yafi, E., & Su'ud, M. M. (2021) · IEEE Access · doi:10.1109/access.2021.3127881 · Cited by 312
Metadata
- Authors
- Nassar, M., Salah, K., ur Rehman, M. H., & Svetinovic, D.
- Venue
- WIREs Data Mining and Knowledge Discovery
- Publisher
- Wiley
- Published
- 2019-10-17
- Volume
- 10
- Issue
- 1
- ISSN
- 1942-4787 (ISSN-L)
- 1942-4795
- OpenAlex
- W2980441098
- Cited by
- 149
- References
- 15
- FWCI
- 6.79
- Type
- journal article
- Language
- en
- Open access
- closed
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.