Research Papers

Cryptocurrency Valuation: An Explainable AI Approach

Yulin Liu, Luyao Zhang

Currently, there are no convincing proxies for the fundamentals of cryptocurrency assets. We propose a new market-to-fundamental ratio, the price-to-utility (PU) ratio, utilizing unique blockchain accounting methods. We then proxy various existing fundamental-to-market ratios by Bitcoin historical data and find they have little predictive power for short-term bitcoin returns. However, PU ratio effectively predicts long-term bitcoin returns than alternative methods. Furthermore, we verify the explainability of PU ratio using machine learning. Finally, we present an automated trading strategy advised by the PU ratio that outperforms the conventional buy-and-hold and market-timing strategies. Our research contributes to explainable AI in finance from three facets: First, our market-to-fundamental ratio is based on classic monetary theory and the unique UTXO model of Bitcoin accounting rather than ad hoc; Second, the empirical evidence testifies the buy-low and sell-high implications of the ratio; Finally, we distribute the trading algorithms as open-source software via Python Package Index for future research, which is exceptional in finance research.

The implementation of Artificial Intelligence (AI) systems in the manufacturing domain enables higher production efficiency, outstanding performance, and safer operations, leveraging powerful tools such as deep learning and reinforcement learning techniques. Despite the high accuracy of these models, they are mostly considered black boxes: they are unintelligible to the human. Opaqueness affects trust in the system, a factor that is critical in the context of decision-making. We present an overview of Explainable Artificial Intelligence (XAI) techniques as a means of boosting the transparency of models. We analyze different metrics to evaluate these techniques and describe several application scenarios in the manufacturing domain.

Safe learning and optimization deals with learning and optimization problems that avoid, as much as possible, the evaluation of non-safe input points, which are solutions, policies, or strategies that cause an irrecoverable loss (e.g., breakage of a machine or equipment, or life threat). Although a comprehensive survey of safe reinforcement learning algorithms was published in 2015, a number of new algorithms have been proposed thereafter, and related works in active learning and in optimization were not considered. This paper reviews those algorithms from a number of domains including reinforcement learning, Gaussian process regression and classification, evolutionary algorithms, and active learning. We provide the fundamental concepts on which the reviewed algorithms are based and a characterization of the individual algorithms. We conclude by explaining how the algorithms are connected and suggestions for future research.

Recent papers in explainable AI have made a compelling case for counterfactual modes of explanation. While counterfactual explanations appear to be extremely effective in some instances, they are formally equivalent to adversarial examples. This presents an apparent paradox for explainability researchers: if these two procedures are formally equivalent, what accounts for the explanatory divide apparent between counterfactual explanations and adversarial examples? We resolve this paradox by placing emphasis back on the semantics of counterfactual expressions. Producing satisfactory explanations for deep learning systems will require that we find ways to interpret the semantics of hidden layer representations in deep neural networks.

Designing Trustworthy AI: A Human-Machine Teaming Framework to Guide Development

Carol J. Smith

Artificial intelligence (AI) holds great promise to empower us with knowledge and augment our effectiveness. We can -- and must -- ensure that we keep humans safe and in control, particularly with regard to government and public sector applications that affect broad populations. How can AI development teams harness the power of AI systems and design them to be valuable to humans? Diverse teams are needed to build trustworthy artificial intelligent systems, and those teams need to coalesce around a shared set of ethics. There are many discussions in the AI field about ethics and trust, but there are few frameworks available for people to use as guidance when creating these systems. The Human-Machine Teaming (HMT) Framework for Designing Ethical AI Experiences described in this paper, when used with a set of technical ethics, will guide AI development teams to create AI systems that are accountable, de-risked, respectful, secure, honest, and usable. To support the team's efforts, activities to understand people's needs and concerns will be introduced along with the themes to support the team's efforts. For example, usability testing can help determine if the audience understands how the AI system works and complies with the HMT Framework. The HMT Framework is based on reviews of existing ethical codes and best practices in human-computer interaction and software development. Human-machine teams are strongest when human users can trust AI systems to behave as expected, safely, securely, and understandably. Using the HMT Framework to design trustworthy AI systems will provide support to teams in identifying potential issues ahead of time and making great experiences for humans.

Purpose: The governance of artificial iintelligence (AI) systems requires a structured approach that connects high-level regulatory principles with practical implementation. Existing frameworks lack clarity on how regulations translate into conformity mechanisms, leading to gaps in compliance and enforcement. This paper addresses this critical gap in AI governance. Methodology/Approach: A five-layer AI governance framework is proposed, spanning from broad regulatory mandates to specific standards, assessment methodologies, and certification processes. By narrowing its scope through progressively focused layers, the framework provides a structured pathway to meet technical, regulatory, and ethical requirements. Its applicability is validated through two case studies on AI fairness and AI incident reporting. Findings: The case studies demonstrate the framework's ability to identify gaps in legal mandates, standardization, and implementation. It adapts to both global and region-specific AI governance needs, mapping regulatory mandates with practical applications to improve compliance and risk management. Practical Implications - By offering a clear and actionable roadmap, this work contributes to global AI governance by equipping policymakers, regulators, and industry stakeholders with a model to enhance compliance and risk management. Social Implications: The framework supports the development of policies that build public trust and promote the ethical use of AI for the benefit of society. Originality/Value: This study proposes a five-layer AI governance framework that bridges high-level regulatory mandates and implementation guidelines. Validated through case studies on AI fairness and incident reporting, it identifies gaps such as missing standardized assessment procedures and reporting mechanisms, providing a structured foundation for targeted governance measures.

Artificial Intelligence (AI) has demonstrated potential in healthcare, particularly in enhancing diagnostic accuracy and decision-making through Clinical Decision Support Systems (CDSSs). However, the successful implementation of these systems relies on user trust and reliance, which can be influenced by explainable AI. This study explores the impact of varying explainability levels on clinicians trust, cognitive load, and diagnostic performance in breast cancer detection. Utilizing an interrupted time series design, we conducted a web-based experiment involving 28 healthcare professionals. The results revealed that high confidence scores substantially increased trust but also led to overreliance, reducing diagnostic accuracy. In contrast, low confidence scores decreased trust and agreement while increasing diagnosis duration, reflecting more cautious behavior. Some explainability features influenced cognitive load by increasing stress levels. Additionally, demographic factors such as age, gender, and professional role shaped participants' perceptions and interactions with the system. This study provides valuable insights into how explainability impact clinicians' behavior and decision-making. The findings highlight the importance of designing AI-driven CDSSs that balance transparency, usability, and cognitive demands to foster trust and improve integration into clinical workflows.

The exponential growth of the Internet of Things (IoT) has significantly increased the complexity and volume of cybersecurity threats, necessitating the development of advanced, scalable, and interpretable security frameworks. This paper presents an innovative, comprehensive framework for real-time IoT attack detection and response that leverages Machine Learning (ML), Explainable AI (XAI), and Large Language Models (LLM). By integrating XAI techniques such as SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) with a model-independent architecture, we ensure our framework's adaptability across various ML algorithms. Additionally, the incorporation of LLMs enhances the interpretability and accessibility of detection decisions, providing system administrators with actionable, human-understandable explanations of detected threats. Our end-to-end framework not only facilitates a seamless transition from model development to deployment but also represents a real-world application capability that is often lacking in existing research. Based on our experiments with the CIC-IOT-2023 dataset \cite{neto2023ciciot2023}, Gemini and OPENAI LLMS demonstrate unique strengths in attack mitigation: Gemini offers precise, focused strategies, while OPENAI provides extensive, in-depth security measures. Incorporating SHAP and LIME algorithms within XAI provides comprehensive insights into attack detection, emphasizing opportunities for model improvement through detailed feature analysis, fine-tuning, and the adaptation of misclassifications to enhance accuracy.

Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy issues, which are exacerbated in critical domains (e.g., healthcare). Moreover, certain application-specific scenarios may require fine-tuning these models on private data. This survey critically examines the privacy threats associated with LLMs, emphasizing the potential for these models to memorize and inadvertently reveal sensitive information. We explore current threats by reviewing privacy attacks on LLMs and propose comprehensive solutions for integrating privacy mechanisms throughout the entire learning pipeline. These solutions range from anonymizing training datasets to implementing differential privacy during training or inference and machine unlearning after training. Our comprehensive review of existing literature highlights ongoing challenges, available tools, and future directions for preserving privacy in LLMs. This work aims to guide the development of more secure and trustworthy AI systems by providing a thorough understanding of privacy preservation methods and their effectiveness in mitigating risks.

Mental health constitutes a complex and pervasive global challenge, affecting millions of lives and often leading to severe consequences. In this paper, we conduct a thorough survey to explore the intersection of data science, artificial intelligence, and mental healthcare, focusing on the recent developments of mental disorder detection through online social media (OSM). A significant portion of the population actively engages in OSM platforms, creating a vast repository of personal data that holds immense potential for mental health analytics. The paper navigates through traditional diagnostic methods, state-of-the-art data- and AI-driven research studies, and the emergence of explainable AI (XAI) models for mental healthcare. We review state-of-the-art machine learning methods, particularly those based on modern deep learning, while emphasising the need for explainability in healthcare AI models. The experimental design section provides insights into prevalent practices, including available datasets and evaluation approaches. We also identify key issues and challenges in the field and propose promising future research directions. As mental health decisions demand transparency, interpretability, and ethical considerations, this paper contributes to the ongoing discourse on advancing XAI in mental healthcare through social media. The comprehensive overview presented here aims to guide researchers, practitioners, and policymakers in developing the area of mental disorder detection.

This chapter explores the foundational concept of robustness in Machine Learning (ML) and its integral role in establishing trustworthiness in Artificial Intelligence (AI) systems. The discussion begins with a detailed definition of robustness, portraying it as the ability of ML models to maintain stable performance across varied and unexpected environmental conditions. ML robustness is dissected through several lenses: its complementarity with generalizability; its status as a requirement for trustworthy AI; its adversarial vs non-adversarial aspects; its quantitative metrics; and its indicators such as reproducibility and explainability. The chapter delves into the factors that impede robustness, such as data bias, model complexity, and the pitfalls of underspecified ML pipelines. It surveys key techniques for robustness assessment from a broad perspective, including adversarial attacks, encompassing both digital and physical realms. It covers non-adversarial data shifts and nuances of Deep Learning (DL) software testing methodologies. The discussion progresses to explore amelioration strategies for bolstering robustness, starting with data-centric approaches like debiasing and augmentation. Further examination includes a variety of model-centric methods such as transfer learning, adversarial training, and randomized smoothing. Lastly, post-training methods are discussed, including ensemble techniques, pruning, and model repairs, emerging as cost-effective strategies to make models more resilient against the unpredictable. This chapter underscores the ongoing challenges and limitations in estimating and achieving ML robustness by existing approaches. It offers insights and directions for future research on this crucial concept, as a prerequisite for trustworthy AI systems.

The agricultural sector plays an essential role in the economic growth of a country. Specifically, in an Indian context, it is the critical source of livelihood for millions of people living in rural areas. Plant Disease is one of the significant factors affecting the agricultural sector. Plants get infected with diseases for various reasons, including synthetic fertilizers, archaic practices, environmental conditions, etc., which impact the farm yield and subsequently hinder the economy. To address this issue, researchers have explored many applications based on AI and Machine Learning techniques to detect plant diseases. This research survey provides a comprehensive understanding of common plant leaf diseases, evaluates traditional and deep learning techniques for disease detection, and summarizes available datasets. It also explores Explainable AI (XAI) to enhance the interpretability of deep learning models' decisions for end-users. By consolidating this knowledge, the survey offers valuable insights to researchers, practitioners, and stakeholders in the agricultural sector, fostering the development of efficient and transparent solutions for combating plant diseases and promoting sustainable agricultural practices.