Research Papers

Artificial intelligence (AI) is reshaping society, from video generation to medical diagnosis, coding agents to autonomous vehicles. Yet researchers, policymakers, and technology companies lack shared terminology for discussing AI risks. Consider "privacy": one framework uses this term to describe a model's ability to leak sensitive training data, while another uses it to mean freedom from government surveillance. Conversely, researchers have introduced "Goodhart's law," "specification gaming," "reward hacking," and "mesa-optimization" to describe the same phenomenon of AI systems optimizing for measured proxies rather than intended goals. This terminological diversity creates friction: comparing findings across studies requires mapping between frameworks, and comprehensive risk coverage requires consulting multiple taxonomies that use different organizing principles. This paper addresses this challenge by creating a comprehensive catalog of AI risks. We systematically analyzed every major AI risk framework published to date-74 frameworks containing 1,725 distinct risks-and organized them into a unified system. Our two classification systems reveal important patterns: contrary to common assumptions, human decisions cause nearly as many AI risks (38%) as the AI systems themselves (42%). The work provides practical tools for anyone working on AI safety, from developers conducting risk assessments to policymakers writing regulations to auditors evaluating AI systems. By establishing a common reference point, this repository creates the foundation for more coordinated and comprehensive approaches to managing AI's risks while realizing its benefits.

Artificial Intelligence (AI) is rapidly integrating into various aspects of our daily lives, influencing decision-making processes in areas such as targeted advertising and matchmaking algorithms. As AI systems become increasingly sophisticated, ensuring their transparency and explainability becomes crucial. Functional transparency is a fundamental aspect of algorithmic decision-making systems, allowing stakeholders to comprehend the inner workings of these systems and enabling them to evaluate their fairness and accuracy. However, achieving functional transparency poses significant challenges that need to be addressed. In this paper, we propose a design for user-centered compliant-by-design transparency in transparent systems. We emphasize that the development of transparent and explainable AI systems is a complex and multidisciplinary endeavor, necessitating collaboration among researchers from diverse fields such as computer science, artificial intelligence, ethics, law, and social science. By providing a comprehensive understanding of the challenges associated with transparency in AI systems and proposing a user-centered design framework, we aim to facilitate the development of AI systems that are accountable, trustworthy, and aligned with societal values.

The rapid development of artificial intelligence (AI) has led to increasing concerns about the capability of AI systems to make decisions and behave responsibly. Responsible AI (RAI) refers to the development and use of AI systems that benefit humans, society, and the environment while minimising the risk of negative consequences. To ensure responsible AI, the risks associated with AI systems' development and use must be identified, assessed and mitigated. Various AI risk assessment frameworks have been released recently by governments, organisations, and companies. However, it can be challenging for AI stakeholders to have a clear picture of the available frameworks and determine the most suitable ones for a specific context. Additionally, there is a need to identify areas that require further research or development of new frameworks, as well as updating and maintaining existing ones. To fill the gap, we present a mapping study of 16 existing AI risk assessment frameworks from the industry, governments, and non-government organizations (NGOs). We identify key characteristics of each framework and analyse them in terms of RAI principles, stakeholders, system lifecycle stages, geographical locations, targeted domains, and assessment methods. Our study provides a comprehensive analysis of the current state of the frameworks and highlights areas of convergence and divergence among them. We also identify the deficiencies in existing frameworks and outlines the essential characteristics of a concrete and connected framework AI risk assessment (C$^2$AIRA) framework. Our findings and insights can help relevant stakeholders choose suitable AI risk assessment frameworks and guide the design of future frameworks towards concreteness and connectedness.

Modern Artificial Intelligence (AI) enabled Intrusion Detection Systems (IDS) are complex black boxes. This means that a security analyst will have little to no explanation or clarification on why an IDS model made a particular prediction. A potential solution to this problem is to research and develop Explainable Intrusion Detection Systems (X-IDS) based on current capabilities in Explainable Artificial Intelligence (XAI). In this paper, we create a Self Organizing Maps (SOMs) based X-IDS system that is capable of producing explanatory visualizations. We leverage SOM's explainability to create both global and local explanations. An analyst can use global explanations to get a general idea of how a particular IDS model computes predictions. Local explanations are generated for individual datapoints to explain why a certain prediction value was computed. Furthermore, our SOM based X-IDS was evaluated on both explanation generation and traditional accuracy tests using the NSL-KDD and the CIC-IDS-2017 datasets.

Federated learning is an emerging privacy-preserving AI technique where clients (i.e., organisations or devices) train models locally and formulate a global model based on the local model updates without transferring local data externally. However, federated learning systems struggle to achieve trustworthiness and embody responsible AI principles. In particular, federated learning systems face accountability and fairness challenges due to multi-stakeholder involvement and heterogeneity in client data distribution. To enhance the accountability and fairness of federated learning systems, we present a blockchain-based trustworthy federated learning architecture. We first design a smart contract-based data-model provenance registry to enable accountability. Additionally, we propose a weighted fair data sampler algorithm to enhance fairness in training data. We evaluate the proposed approach using a COVID-19 X-ray detection use case. The evaluation results show that the approach is feasible to enable accountability and improve fairness. The proposed algorithm can achieve better performance than the default federated learning setting in terms of the model's generalisation and accuracy.

Limited expert time is a key bottleneck in medical imaging. Due to advances in image classification, AI can now serve as decision-support for medical experts, with the potential for great gains in radiologist productivity and, by extension, public health. However, these gains are contingent on building and maintaining experts' trust in the AI agents. Explainable AI may build such trust by helping medical experts to understand the AI decision processes behind diagnostic judgements. Here we introduce and evaluate explanations based on Bayesian Teaching, a formal account of explanation rooted in the cognitive science of human learning. We find that medical experts exposed to explanations generated by Bayesian Teaching successfully predict the AI's diagnostic decisions and are more likely to certify the AI for cases when the AI is correct than when it is wrong, indicating appropriate trust. These results show that Explainable AI can be used to support human-AI collaboration in medical imaging.

The use of algorithmic (learning-based) decision making in scenarios that affect human lives has motivated a number of recent studies to investigate such decision making systems for potential unfairness, such as discrimination against subjects based on their sensitive features like gender or race. However, when judging the fairness of a newly designed decision making system, these studies have overlooked an important influence on people's perceptions of fairness, which is how the new algorithm changes the status quo, i.e., decisions of the existing decision making system. Motivated by extensive literature in behavioral economics and behavioral psychology (prospect theory), we propose a notion of fair updates that we refer to as loss-averse updates. Loss-averse updates constrain the updates to yield improved (more beneficial) outcomes to subjects compared to the status quo. We propose tractable proxy measures that would allow this notion to be incorporated in the training of a variety of linear and non-linear classifiers. We show how our proxy measures can be combined with existing measures for training nondiscriminatory classifiers. Our evaluation using synthetic and real-world datasets demonstrates that the proposed proxy measures are effective for their desired tasks.

When we consult with a doctor, lawyer, or financial advisor, we generally assume that they are acting in our best interests. But what should we assume when it is an artificial intelligence (AI) system that is acting on our behalf? Early examples of AI assistants like Alexa, Siri, Google, and Cortana already serve as a key interface between consumers and information on the web, and users routinely rely upon AI-driven systems like these to take automated actions or provide information. Superficially, such systems may appear to be acting according to user interests. However, many AI systems are designed with embedded conflicts of interests, acting in ways that subtly benefit their creators (or funders) at the expense of users. To address this problem, in this paper we introduce the concept of AI loyalty. AI systems are loyal to the degree that they are designed to minimize, and make transparent, conflicts of interest, and to act in ways that prioritize the interests of users. Properly designed, such systems could have considerable functional and competitive - not to mention ethical - advantages relative to those that do not. Loyal AI products hold an obvious appeal for the end-user and could serve to promote the alignment of the long-term interests of AI developers and customers. To this end, we suggest criteria for assessing whether an AI system is sufficiently transparent about conflicts of interest, and acting in a manner that is loyal to the user, and argue that AI loyalty should be considered during the technological design process alongside other important values in AI ethics such as fairness, accountability privacy, and equity. We discuss a range of mechanisms, from pure market forces to strong regulatory frameworks, that could support incorporation of AI loyalty into a variety of future AI systems.

As freelancing work keeps on growing almost everywhere due to a sharp decrease in communication costs and to the widespread of Internet-based labour marketplaces (e.g., guru.com, feelancer.com, mturk.com, upwork.com), many researchers and practitioners have started exploring the benefits of outsourcing and crowdsourcing. Since employers often use these platforms to find a group of workers to complete a specific task, researchers have focused their efforts on the study of team formation and matching algorithms and on the design of effective incentive schemes. Nevertheless, just recently, several concerns have been raised on possibly unfair biases introduced through the algorithms used to carry out these selection and matching procedures. For this reason, researchers have started studying the fairness of algorithms related to these online marketplaces, looking for intelligent ways to overcome the algorithmic bias that frequently arises. Broadly speaking, the aim is to guarantee that, for example, the process of hiring workers through the use of machine learning and algorithmic data analysis tools does not discriminate, even unintentionally, on grounds of nationality or gender. In this short paper, we define the Fair Team Formation problem in the following way: given an online labour marketplace where each worker possesses one or more skills, and where all workers are divided into two or more not overlapping classes (for examples, men and women), we want to design an algorithm that is able to find a team with all the skills needed to complete a given task, and that has the same number of people from all classes. We provide inapproximability results for the Fair Team Formation problem together with four algorithms for the problem itself. We also tested the effectiveness of our algorithmic solutions by performing experiments using real data from an online labor marketplace.

Always Lurking: Understanding and Mitigating Bias in Online Human Trafficking Detection

Kyle Hundman, Thamme Gowda, Mayank Kejriwal +1

Web-based human trafficking activity has increased in recent years but it remains sparsely dispersed among escort advertisements and difficult to identify due to its often-latent nature. The use of intelligent systems to detect trafficking can thus have a direct impact on investigative resource allocation and decision-making, and, more broadly, help curb a widespread social problem. Trafficking detection involves assigning a normalized score to a set of escort advertisements crawled from the Web -- a higher score indicates a greater risk of trafficking-related (involuntary) activities. In this paper, we define and study the problem of trafficking detection and present a trafficking detection pipeline architecture developed over three years of research within the DARPA Memex program. Drawing on multi-institutional data, systems, and experiences collected during this time, we also conduct post hoc bias analyses and present a bias mitigation plan. Our findings show that, while automatic trafficking detection is an important application of AI for social good, it also provides cautionary lessons for deploying predictive machine learning algorithms without appropriate de-biasing. This ultimately led to integration of an interpretable solution into a search system that contains over 100 million advertisements and is used by over 200 law enforcement agencies to investigate leads.

We present our Balanced, Integrated and Grounded (BIG) argument for assuring the safety of AI systems. The BIG argument adopts a whole-system approach to constructing a safety case for AI systems of varying capability, autonomy and criticality. Firstly, it is balanced by addressing safety alongside other critical ethical issues such as privacy and equity, acknowledging complexities and trade-offs in the broader societal impact of AI. Secondly, it is integrated by bringing together the social, ethical and technical aspects of safety assurance in a way that is traceable and accountable. Thirdly, it is grounded in long-established safety norms and practices, such as being sensitive to context and maintaining risk proportionality. Whether the AI capability is narrow and constrained or general-purpose and powered by a frontier or foundational model, the BIG argument insists on a systematic treatment of safety. Further, it places a particular focus on the novel hazardous behaviours emerging from the advanced capabilities of frontier AI models and the open contexts in which they are rapidly being deployed. These complex issues are considered within a wider AI safety case, approaching assurance from both technical and sociotechnical perspectives. Examples illustrating the use of the BIG argument are provided throughout the paper.

Practitioners and researchers trying to strike a balance between accuracy and transparency center Explainable Artificial Intelligence (XAI) at the junction of finance. This paper offers a thorough overview of the changing scene of XAI applications in finance together with domain-specific implementations, methodological developments, and trend mapping of research. Using bibliometric and content analysis, we find topic clusters, significant research, and most often used explainability strategies used in financial industries. Our results show a substantial dependence on post-hoc interpretability techniques; attention mechanisms, feature importance analysis and SHAP are the most often used techniques among them. This review stresses the need of multidisciplinary approaches combining financial knowledge with improved explainability paradigms and exposes important shortcomings in present XAI systems.