The Metaverse is an online universe that combines virtual reality and augmented reality, linked together via a network.It has generated novel experiences that are fully engaging and transpire in real time, facilitating interpersonal communication and dialogue. Virtual environments with 3D space and avatars can boost patient-facing platforms, operational utilisation, digital education, diagnostics, and treatment choices in medicine and ophthalmology. Globally, there is an increasing prevalence of chronic diseases, with an estimated 25 percent of individuals presently contending with multiple chronic health issues. The management of chronic diseases is currently being rethought in light of the development of technology known together as "Smart Healthcare." A prime example is state-of-the-art wearable technology that incentivizes people to embrace healthier lifestyles through the monitoring of physiological indicators and metabolic processes. With better data organisation and analysis, chronic disease patients may benefit from improved health, privacy, and quality of life. Through the examination of physiological data acquired from wearable devices on a patient, Artificial Intelligence (AI) has the capability to generate informed recommendations pertaining to the diagnosis and treatment of illness. These recommendations can be provided by AI. The adoption of blockchain technology (BC) has the potential to significantly advance healthcare in a variety of ways, including decentralised data sharing, user privacy, user empowerment, and dependability in data administration. The potential impact of Wearable Technologies (WT), Artificial Intelligence (AI), and Blockchain Technology (BC) on Chronic Disease Management (CDM) could be a transition in emphasis from the hospital to the patient. This article provides a patient-centered technical framework for controlling chronic diseases using artificial intelligence, blockchain, and wearable technologies. Our proposed architecture depends on Metaverse environment. In order to participate in the Metaverse, both patients and physicians need to sign up on the Blockchain network. After entering, customers will be accompanied by avatars throughout the experience. A comprehensive record of all information gathered during doctor-patient consultations, including text, videos, images, audio, and clinical data, will be compiled, uploaded to the blockchain, and stored in perpetuity. Explainable Artificial Intelligence (XAI) algorithms examine these particulars in order to diagnose and forecast the progression of diseases. We conclude with a discussion of the constraints of this novel paradigm and recommendations for future research.
Intelligent human inputs are required both in the training and operation of AI systems, and within the governance of blockchain systems and decentralized autonomous organizations (DAOs). This paper presents a formal definition of Human Intelligence Primitives (HIPs), and describes the design and implementation of an Ethereum protocol for their on-chain collection, modeling, and integration in machine learning workflows.
Deep learning techniques can predict cognitive intelligence from large datasets involving complex computations with activation functions. However, the prediction output needs verification for trust and reliability. Moreover, these algorithms suffer from the model's provenance to keep track of model updates and developments. Blockchain smart contracts provide a trustable ledger with consensus-based decisions that assure integrity and verifiability. In addition, the immutability feature of blockchain also supports the provenance of data that can help deep learning algorithms. Nevertheless, smart contract languages cannot predict due to the absence of floating-point operations required by activation functions of neural networks. In this paper, we derive a novel method using the Taylor series expansion to compute the floating-point equivalent output for activation functions. We train the deep learning model off-chain using a standard Python programming language. Moreover, we store models and predict on-chain with blockchain smart contracts to produce a trusted forecast. Our experiment and analysis achieved an accuracy (99%) similar to popular Keras Python library models for the MNIST dataset. Furthermore, any blockchain platform can reproduce the activation function using our derived method. Last but not least, other deep learning algorithms can reuse the mathematical model to predict on-chain.
In the last decade, cryptocurrency trading has attracted the attention of private and professional traders and investors. To forecast the financial markets, algorithmic trading systems based on Artificial Intelligence (AI) models are becoming more and more established. However, they suffer from the lack of transparency, thus hindering domain experts from directly monitoring the fundamentals behind market movements. This is particularly critical for cryptocurrency investors, because the study of the main factors influencing cryptocurrency prices, including the characteristics of the blockchain infrastructure, is crucial for driving experts’ decisions. This paper proposes a new visual analytics tool to support domain experts in the explanation of AI-based cryptocurrency trading systems. To describe the rationale behind AI models, it exploits an established method, namely SHapley Additive exPlanations, which allows experts to identify the most discriminating features and provides them with an interactive and easy-to-use graphical interface. The simulations carried out on 21 cryptocurrencies over a 8-year period demonstrate the usability of the proposed tool.
Cryptocurrency blockchain data encounter a class-imbalance problem due to only a few known labels of illicit or fraudulent activities in the blockchain network. For this purpose, we seek to compare various resampling methods applied to two highly imbalanced datasets derived from the blockchain of Bitcoin and Ethereum after further dimensionality reductions, which is different from previous studies on these datasets. Firstly, we study the performance of various classical supervised learning methods to classify illicit transactions or accounts on Bitcoin or Ethereum datasets, respectively. Consequently, we apply various resampling techniques to these datasets using the best performing learning algorithm on each of these datasets. Subsequently, we study the feature importance of the given models, wherein the resampled datasets directly influenced on the explainability of the model. Our main finding is that undersampling using the edited nearest-neighbour technique has attained an accuracy of more than 99% on the given datasets by removing the noisy data points from the whole dataset. Moreover, the best-performing learning algorithms have shown superior performance after feature reduction on these datasets in comparison to their original studies. The matchless contribution lies in discussing the effect of the data resampling on feature importance which is interconnected with explainable artificial intelligence (XAI) techniques.
Blockchain technology has transformed digital transactions into decentralized, transparent, and immutable systems. Smart contracts running on platforms like Ethereum enable automated agreements without intermediaries, but they remain vulnerable to logical errors and security risks that can lead to financial losses. This paper presents a systematic study on AI-based smart contract analysis, using machine learning and deep learning to detect vulnerabilities, anomalies, and potential risks. It proposes a hybrid model combining static analysis (code-level error detection), dynamic analysis (runtime monitoring), and supervised/unsupervised learning techniques. Feature extraction methods convert contract code into formats suitable for AI processing. The approach integrates rule-based systems with AI models to improve detection accuracy and reduce false positives. Evaluation on benchmark datasets shows better performance than traditional methods. The study highlights the effectiveness of AI in enhancing smart contract security and suggests future work on explainable AI, real-time monitoring, and cross-platform interoperability.
Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced. As these applications make high-stake decisions and involve societal values like fairness and transparency, it is critical to explain the learned models. We aim to study post-hoc explanations of Siamese networks (SN) widely used in learning to compare. We characterize the instability of gradient-based explanations due to the additional compared object in SN, in contrast to architectures with a single input instance. We propose an optimization framework that derives global invariance from unlabeled data using self-learning to promote the stability of local explanations tailored for specific query-reference pairs. The optimization problems can be solved using gradient descent-ascent (GDA) for constrained optimization, or SGD for KL-divergence regularized unconstrained optimization, with convergence proofs, especially when the objective functions are nonconvex due to the Siamese architecture. Quantitative results and case studies on tabular and graph data from neuroscience and chemical engineering show that the framework respects the self-learned invariance while robustly optimizing the faithfulness and simplicity of the explanation. We further demonstrate the convergence of GDA experimentally.
Abstract The past few years have witnessed the resurgence of uncertainty estimation generally in neural networks. Providing uncertainty quantification besides the predictive probability is desirable to reflect the degree of belief in the model’s decision about a given input. Recently, Monte-Carlo dropout (MC-dropout) method has been introduced as a probabilistic approach based Bayesian approximation which is computationally efficient than Bayesian neural networks. MC-dropout has revealed promising results on image datasets regarding uncertainty quantification. However, this method has been subjected to criticism regarding the behaviour of MC-dropout and what type of uncertainty it actually captures. For this purpose, we aim to discuss the behaviour of MC-dropout on classification tasks using synthetic and real data. We empirically explain different cases of MC-dropout that reflects the relative merits of this method. Our main finding is that MC-dropout captures datapoints lying on the decision boundary between the opposed classes using synthetic data. On the other hand, we apply MC-dropout method on dataset derived from Bitcoin known as Elliptic data to highlight the outperformance of model with MC-dropout over standard model. A conclusion and possible future directions are proposed.
Explainable Artificial Intelligence (XAI) generates explanations which are used by regulators to audit the responsibility in case of any catastrophic failure. These explanations are currently stored in centralized systems. However, due to lack of security and traceability in centralized systems, the respective owner may temper the explanations for his convenience in order to avoid any penalty. Nowadays, Blockchain has emerged as one of the promising technologies that might overcome the security limitations. Hence, in this paper, we propose a novel Blockchain based framework for proof-of-authenticity pertaining to XAI decisions. The framework stores the explanations in InterPlanetary File System (IPFS) due to storage limitations of Ethereum Blockchain. Further, a Smart Contract is designed and deployed in order to supervise the storage and retrieval of explanations from Ethereum Blockchain. Furthermore, to induce cryptographic security in the network, an explanation's hash is calculated and stored in Blockchain too. Lastly, we perform the cost and security analysis of our proposed system.
Clément Bénard, Gérard Biau, Sébastien da Veiga, Erwan Scornet
We introduce SIRUS (Stable and Interpretable RUle Set) for regression, a stable rule learning algorithm which takes the form of a short and simple list of rules. State-of-the-art learning algorithms are often referred to as "black boxes" because of the high number of operations involved in their prediction process. Despite their powerful predictivity, this lack of interpretability may be highly restrictive for applications with critical decisions at stake. On the other hand, algorithms with a simple structure-typically decision trees, rule algorithms, or sparse linear models-are well known for their instability. This undesirable feature makes the conclusions of the data analysis unreliable and turns out to be a strong operational limitation. This motivates the design of SIRUS, which combines a simple structure with a remarkable stable behavior when data is perturbed. The algorithm is based on random forests, the predictive accuracy of which is preserved. We demonstrate the efficiency of the method both empirically (through experiments) and theoretically (with the proof of its asymptotic stability). Our R/C++ software implementation sirus is available from CRAN.
shows that transformers can act as "soft theorem provers" by answering questions over explicitly provided knowledge in natural language. In our work, we take a step closer to emulating formal theorem provers, by proposing PROVER, an interpretable transformer-based model that jointly answers binary questions over rule-bases and generates the corresponding proofs. Our model learns to predict nodes and edges corresponding to proof graphs in an efficient constrained training paradigm. During inference, a valid proof, satisfying a set of global constraints is generated. We conduct experiments on synthetic, hand-authored, and human-paraphrased rule-bases to show promising results for QA and proof generation, with strong generalization performance. First, PROVER generates proofs with an accuracy of 87%, while retaining or improving performance on the QA task, compared to RuleTakers (up to 6% improvement on zero-shot evaluation). Second, when trained on questions requiring lower depths of reasoning, it generalizes significantly better to higher depths (up to 15% improvement). Third, PROVER obtains near perfect QA accuracy of 98% using only 40% of the training data. However, generating proofs for questions requiring higher depths of reasoning becomes challenging, and the accuracy drops to 65% for "depth 5", indicating significant scope for future work.
Machine learning has recently enabled large advances in artificial intelligence, but these results can be highly centralized. The large datasets required are generally proprietary; predictions are often sold on a per-query basis; and published models can quickly become out of date without effort to acquire more data and maintain them. Published proposals to provide models and data for free for certain tasks include Microsoft Research's Decentralized and Collaborative AI on Blockchain. The framework allows participants to collaboratively build a dataset and use smart contracts to share a continuously updated model on a public blockchain. The initial proposal gave an overview of the framework omitting many details of the models used and the incentive mechanisms in real world scenarios. In this work, we evaluate the use of several models and configurations in order to propose best practices when using the Self-Assessment incentive mechanism so that models can remain accurate and well-intended participants that submit correct data have the chance to profit. We have analyzed simulations for each of three models: Perceptron, Naïve Bayes, and a Nearest Centroid Classifier, with three different datasets: predicting a sport with user activity from Endomondo, sentiment analysis on movie reviews from IMDB, and determining if a news article is fake. We compare several factors for each dataset when models are hosted in smart contracts on a public blockchain: their accuracy over time, balances of a good and bad user, and transaction costs (or gas) for deploying, updating, collecting refunds, and collecting rewards. A free and open source implementation for the Ethereum blockchain and simulations written in Python is provided at https://github.com/microsoft/0xDeCA10B. This version has updated gas costs using newer optimizations written after the original publication.
Mohamed Nassar, Khaled Salah, Muhammad Habib ur Rehman, Davor Svetinović
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
Using blockchain technology, it is possible to create contracts that offer a reward in exchange for a trained machine learning model for a particular data set. This would allow users to train machine learning models for a reward in a trustless manner. The smart contract will use the blockchain to automatically validate the solution, so there would be no debate about whether the solution was correct or not. Users who submit the solutions won't have counterparty risk that they won't get paid for their work. Contracts can be created easily by anyone with a dataset, even programmatically by software agents. This creates a market where parties who are good at solving machine learning problems can directly monetize their skillset, and where any organization or software agent that has a problem to solve with AI can solicit solutions from all over the world. This will incentivize the creation of better machine learning models, and make AI more accessible to companies and software agents.
Artificial intelligence (AI) delivers numerous chances to add to the prosperity of people and the stability of economies and society, yet besides, it adds up a variety of novel moral, legal, social, and innovative difficulties. Trustworthy AI (TAI) bases on the possibility that trust builds the establishment of various societies, economies, and sustainable turn of events, and that people, organizations, and societies can along these lines just at any point understand the maximum capacity of AI, if trust can be set up in its development, deployment, and use. The risks of unintended and negative outcomes related to AI are proportionately high, particularly at scale. Most AI is really artificial narrow intelligence, intended to achieve a specific task on previously curated information from a certain source. Since most AI models expand on correlations, predictions could fail to sum up to various populations or settings and might fuel existing disparities and biases. As the AI industry is amazingly imbalanced, and experts are as of now overpowered by other digital devices, there could be a little capacity to catch blunders. With this article, we aim to present the idea of TAI and its five essential standards (1) usefulness, (2) non-maleficence, (3) autonomy, (4) justice, and (5) logic. We further draw on these five standards to build up a data-driven analysis for TAI and present its application by portraying productive paths for future research, especially as to the distributed ledger technology-based acknowledgment of TAI.
Open access
Artificial Intelligence in Healthcare and Education