Research Papers

Biases in large-scale image datasets are known to influence the performance of computer vision models as a function of geographic context. To investigate the limitations of standard Internet data collection methods in low- and middle-income countries, we analyze human-centric image geo-diversity on a massive scale using geotagged Flickr images associated with each nation in Africa. We report the quantity and content of available data with comparisons to population-matched nations in Europe as well as the distribution of data according to fine-grained intra-national wealth estimates. Temporal analyses are performed at two-year intervals to expose emerging data trends. Furthermore, we present findings for an ``othering'' phenomenon as evidenced by a substantial number of images from Africa being taken by non-local photographers. The results of our study suggest that further work is required to capture image data representative of African people and their environments and, ultimately, to improve the applicability of computer vision models in a global context.

Argument Attribution Explanations in Quantitative Bipolar Argumentation Frameworks (Technical Report)

Xiang Yin, Nico Potyka, Francesca Toni

Argumentative explainable AI has been advocated by several in recent years, with an increasing interest on explaining the reasoning outcomes of Argumentation Frameworks (AFs). While there is a considerable body of research on qualitatively explaining the reasoning outcomes of AFs with debates/disputes/dialogues in the spirit of extension-based semantics, explaining the quantitative reasoning outcomes of AFs under gradual semantics has not received much attention, despite widespread use in applications. In this paper, we contribute to filling this gap by proposing a novel theory of Argument Attribution Explanations (AAEs) by incorporating the spirit of feature attribution from machine learning in the context of Quantitative Bipolar Argumentation Frameworks (QBAFs): whereas feature attribution is used to determine the influence of features towards outputs of machine learning models, AAEs are used to determine the influence of arguments towards topic arguments of interest. We study desirable properties of AAEs, including some new ones and some partially adapted from the literature to our setting. To demonstrate the applicability of our AAEs in practice, we conclude by carrying out two case studies in the scenarios of fake news detection and movie recommender systems.

Invisible Users: Uncovering End-Users' Requirements for Explainable AI via Explanation Forms and Goals

Weina Jin, Jianyu Fan, Diane Gromala +2

Non-technical end-users are silent and invisible users of the state-of-the-art explainable artificial intelligence (XAI) technologies. Their demands and requirements for AI explainability are not incorporated into the design and evaluation of XAI techniques, which are developed to explain the rationales of AI decisions to end-users and assist their critical decisions. This makes XAI techniques ineffective or even harmful in high-stakes applications, such as healthcare, criminal justice, finance, and autonomous driving systems. To systematically understand end-users' requirements to support the technical development of XAI, we conducted the EUCA user study with 32 layperson participants in four AI-assisted critical tasks. The study identified comprehensive user requirements for feature-, example-, and rule-based XAI techniques (manifested by the end-user-friendly explanation forms) and XAI evaluation objectives (manifested by the explanation goals), which were shown to be helpful to directly inspire the proposal of new XAI algorithms and evaluation metrics. The EUCA study findings, the identified explanation forms and goals for technical specification, and the EUCA study dataset support the design and evaluation of end-user-centered XAI techniques for accessible, safe, and accountable AI.

Deep visual models have widespread applications in high-stake domains. Hence, their black-box nature is currently attracting a large interest of the research community. We present the first survey in Explainable AI that focuses on the methods and metrics for interpreting deep visual models. Covering the landmark contributions along the state-of-the-art, we not only provide a taxonomic organization of the existing techniques, but also excavate a range of evaluation metrics and collate them as measures of different properties of model explanations. Along the insightful discussion on the current trends, we also discuss the challenges and future avenues for this research direction.

Atomist or Holist? A Diagnosis and Vision for More Productive Interdisciplinary AI Ethics Dialogue

Travis Greene, Amit Dhurandhar, Galit Shmueli

In response to growing recognition of the social impact of new AI-based technologies, major AI and ML conferences and journals now encourage or require papers to include ethics impact statements and undergo ethics reviews. This move has sparked heated debate concerning the role of ethics in AI research, at times devolving into name-calling and threats of "cancellation." We diagnose this conflict as one between atomist and holist ideologies. Among other things, atomists believe facts are and should be kept separate from values, while holists believe facts and values are and should be inextricable from one another. With the goal of reducing disciplinary polarization, we draw on numerous philosophical and historical sources to describe each ideology's core beliefs and assumptions. Finally, we call on atomists and holists within the ever-expanding data science community to exhibit greater empathy during ethical disagreements and propose four targeted strategies to ensure AI research benefits society.

Machine Learning has become an integral part of engineering design and decision making in several domains, including sports. Deep Neural Networks (DNNs) have been the state-of-the-art methods for predicting outcomes of professional sports events. However, apart from getting highly accurate predictions on these sports events outcomes, it is necessary to answer questions such as "Why did the model predict that Team A would win Match X against Team B?" DNNs are inherently black-box in nature. Therefore, it is required to provide high-quality interpretable, and understandable explanations for a model's prediction in sports. This paper explores a two-phased Explainable Artificial Intelligence(XAI) approach to predict outcomes of matches in the Brazilian volleyball League (SuperLiga). In the first phase, we directly use the interpretable rule-based ML models that provide a global understanding of the model's behaviors based on Boolean Rule Column Generation (BRCG; extracts simple AND-OR classification rules) and Logistic Regression (LogReg; allows to estimate the feature importance scores). In the second phase, we construct non-linear models such as Support Vector Machine (SVM) and Deep Neural Network (DNN) to obtain predictive performance on the volleyball matches' outcomes. We construct the "post-hoc" explanations for each data instance using ProtoDash, a method that finds prototypes in the training dataset that are most similar to the test instance, and SHAP, a method that estimates the contribution of each feature on the model's prediction. We evaluate the SHAP explanations using the faithfulness metric. Our results demonstrate the effectiveness of the explanations for the model's predictions.

Towards Implementing Responsible AI

Conrad Sanderson, Qinghua Lu, David Douglas +3

As the deployment of artificial intelligence (AI) is changing many fields and industries, there are concerns about AI systems making decisions and recommendations without adequately considering various ethical aspects, such as accountability, reliability, transparency, explainability, contestability, privacy, and fairness. While many sets of AI ethics principles have been recently proposed that acknowledge these concerns, such principles are high-level and do not provide tangible advice on how to develop ethical and responsible AI systems. To gain insight on the possible implementation of the principles, we conducted an empirical investigation involving semi-structured interviews with a cohort of AI practitioners. The salient findings cover four aspects of AI system design and development, adapting processes used in software engineering: (i) high-level view, (ii) requirements engineering, (iii) design and implementation, (iv) deployment and operation.

Following on from the publication of its Feasibility Study in December 2020, the Council of Europe's Ad Hoc Committee on Artificial Intelligence (CAHAI) and its subgroups initiated efforts to formulate and draft its Possible Elements of a Legal Framework on Artificial Intelligence, based on the Council of Europe's standards on human rights, democracy, and the rule of law. This document was ultimately adopted by the CAHAI plenary in December 2021. To support this effort, The Alan Turing Institute undertook a programme of research that explored the governance processes and practical tools needed to operationalise the integration of human right due diligence with the assurance of trustworthy AI innovation practices. The resulting framework was completed and submitted to the Council of Europe in September 2021. It presents an end-to-end approach to the assurance of AI project lifecycles that integrates context-based risk analysis and appropriate stakeholder engagement with comprehensive impact assessment, and transparent risk management, impact mitigation, and innovation assurance practices. Taken together, these interlocking processes constitute a Human Rights, Democracy and the Rule of Law Assurance Framework (HUDERAF). The HUDERAF combines the procedural requirements for principles-based human rights due diligence with the governance mechanisms needed to set up technical and socio-technical guardrails for responsible and trustworthy AI innovation practices. Its purpose is to provide an accessible and user-friendly set of mechanisms for facilitating compliance with a binding legal framework on artificial intelligence, based on the Council of Europe's standards on human rights, democracy, and the rule of law, and to ensure that AI innovation projects are carried out with appropriate levels of public accountability, transparency, and democratic governance.

In this paper, we critically examine the effectiveness of the requirement to conduct a Data Protection Impact Assessment (DPIA) in Article 35 of the General Data Protection Regulation (GDPR) in light of fairness metrics. Through this analysis, we explore the role of the fairness principle as introduced in Article 5(1)(a) and its multifaceted interpretation in the obligation to conduct a DPIA. Our paper argues that although there is a significant theoretical role for the considerations of fairness in the DPIA process, an analysis of the various guidance documents issued by data protection authorities on the obligation to conduct a DPIA reveals that they rarely mention the fairness principle in practice.

Applications of deep learning to synthetic media generation allow the creation of convincing forgeries, called DeepFakes, with limited technical expertise. DeepFake detection is an increasingly active research area. In this paper, we analyze an existing DeepFake detection technique based on head pose estimation, which can be applied when fake images are generated with an autoencoder-based face swap. Existing literature suggests that this method is an effective DeepFake detector, and its motivating principles are attractively simple. With an eye towards using these principles to develop new DeepFake detectors, we conduct a reproducibility study of the existing method. We conclude that its merits are dramatically overstated, despite its celebrated status. By investigating this discrepancy we uncover a number of important and generalizable insights related to facial landmark detection, identity-agnostic head pose estimation, and algorithmic bias in DeepFake detectors. Our results correct the current literature's perception of state of the art performance for DeepFake detection.

Desiderata for Explainable AI in statistical production systems of the European Central Bank

Carlos Mougan, Georgios Kanellos, Thomas Gottron

Explainable AI constitutes a fundamental step towards establishing fairness and addressing bias in algorithmic decision-making. Despite the large body of work on the topic, the benefit of solutions is mostly evaluated from a conceptual or theoretical point of view and the usefulness for real-world use cases remains uncertain. In this work, we aim to state clear user-centric desiderata for explainable AI reflecting common explainability needs experienced in statistical production systems of the European Central Bank. We link the desiderata to archetypical user roles and give examples of techniques and methods which can be used to address the user's needs. To this end, we provide two concrete use cases from the domain of statistical data production in central banks: the detection of outliers in the Centralised Securities Database and the data-driven identification of data quality checks for the Supervisory Banking data system.

Electronic Health Records (EHRs) provide a wealth of information for machine learning algorithms to predict the patient outcome from the data including diagnostic information, vital signals, lab tests, drug administration, and demographic information. Machine learning models can be built, for example, to evaluate patients based on their predicted mortality or morbidity and to predict required resources for efficient resource management in hospitals. In this paper, we demonstrate that an attacker can manipulate the machine learning predictions with EHRs easily and selectively at test time by backdoor attacks with the poisoned training data. Furthermore, the poison we create has statistically similar features to the original data making it hard to detect, and can also attack multiple machine learning models without any knowledge of the models. With less than 5% of the raw EHR data poisoned, we achieve average attack success rates of 97% on mortality prediction tasks with MIMIC-III database against Logistic Regression, Multilayer Perceptron, and Long Short-term Memory models simultaneously.