Blockchain for explainable and trustworthy artificial intelligence

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

Artificial Intelligence and Bank Soundness: Between the Devil and the Deep Blue Sea - Part 2

“…Transparency is also important to fully trust the system through validating the decision made by AI, by not only detecting anomalies in the decision process such as biasness, mistakes, manipulations of data, deficiencies, compliance to rules i.e. GDPR, cybersecurity crimes linked to work processes such as dataset poisoning, internal network manipulation, and side-channel attacks [69] but also to detect clearly and precisely at which step the anomalies occurred and what information AI fed itself [10,12,64,[66][67][68][70][71][72].…”

“…AI that are trained based on supervised learning where both inputs and output are fed into the system have zero chance of biasness unless the data fed itself is biased. Data used to train ML algorithm must be representative of a wide range of customers that will apply for loans representing namely a whole population [27,72]. If a population is underrepresented or there are rare cases such as women, race, ethnicity, marital status, zero credit history and this information is used to train AI, AI will deliver biased results if data is highly correlated in these categories [7,28,[72][73][74].…”

“…Each staff has established procedures to part with AI and their responsibilities have been distributed widely amongst them. As such, when a catastrophe strikes, it would be difficult to assign liability and could be a perfect cover for mistakes, manipulation and exploitation [64,72,79]. In the pursuit of accumulating big data, banks could cross the boundaries to incorporate customers private information.…”

“…As AI systems are interconnected, hackers or malicious software can manipulate bank's data by hacking client's financial details, creating false identities, flooding systems with fabricated data resulting in misclassification or bad clusters causing incorrect decisions facing consumer backlash and regulatory repercussions [28,72].…”

Blockchain Technology for Smart Grids: Decentralized NIST Conceptual Model

“…Besides the financial industry, we have also seen a significant rise of interest in blockchain technology in other domains [4], [5]. This interest has become evident in complex engineering domains such as energy and the Internet The associate editor coordinating the review of this manuscript and approving it for publication was Shichao Liu . of Things (IoT).…”