Research Papers

Over the last few years, the number of works about deep learning applied to the medical field has increased enormously. The necessity of a rigorous assessment of these models is required to explain these results to all people involved in medical exams. A recent field in the machine learning area is explainable artificial intelligence, also known as XAI, which targets to explain the results of such black box models to permit the desired assessment. This survey analyses several recent studies in the XAI field applied to medical diagnosis research, allowing some explainability of the machine learning results in several different diseases, such as cancers and COVID-19.

Human-AI decision making is becoming increasingly ubiquitous, and explanations have been proposed to facilitate better Human-AI interactions. Recent research has investigated the positive impact of explanations on decision subjects' fairness perceptions in algorithmic decision-making. Despite these advances, most studies have captured the effect of explanations in isolation, considering explanations as ends in themselves, and reducing them to technical solutions provided through XAI methodologies. In this vision paper, we argue that the effect of explanations on fairness perceptions should rather be captured in relation to decision subjects' right to contest such decisions. Since contestable AI systems are open to human intervention throughout their lifecycle, contestability requires explanations that go beyond outcomes and also capture the rationales that led to the development and deployment of the algorithmic system in the first place. We refer to such explanations as process-centric explanations. In this work, we introduce the notion of process-centric explanations and describe some of the main challenges and research opportunities for generating and evaluating such explanations.

In this 4-page manuscript we discuss the problem of long-term AI Safety from a Software Engineering (SE) research viewpoint. We briefly summarize long-term AI Safety, and the challenge of avoiding harms from AI as systems meet or exceed human capabilities, including software engineering capabilities (and approach AGI / "HLMI"). We perform a quantified literature review suggesting that AI Safety discussions are not common at SE venues. We make conjectures about how software might change with rising capabilities, and categorize "subproblems" which fit into traditional SE areas, proposing how work on similar problems might improve the future of AI and SE.

In the field of functional genomics, the analysis of gene expression profiles through Machine and Deep Learning is increasingly providing meaningful insight into a number of diseases. The paper proposes a novel algorithm to perform Feature Selection on genomic-scale data, which exploits the reconstruction capabilities of autoencoders and an ad-hoc defined Explainable Artificial Intelligence-based score in order to select the most informative genes for diagnosis, prognosis, and precision medicine. Results of the application on a Chronic Lymphocytic Leukemia dataset evidence the effectiveness of the algorithm, by identifying and suggesting a set of meaningful genes for further medical investigation.

Deep Learning (DL) is one of the most popular research topics in machine learning and DL-driven image recognition systems have developed rapidly. Recent research has employed metamorphic testing (MT) to detect misclassified images. Most of them discuss metamorphic relations (MR), with limited attention given to which regions should be transformed. We focus on the fact that there are sensitive regions where even small transformations can easily change the prediction results and propose an MT framework that efficiently tests for regions prone to misclassification by transforming these sensitive regions. Our evaluation demonstrated that the sensitive regions can be specified by Explainable AI (XAI) and our framework effectively detects faults.

The Casual Conversations v2 Dataset

Bilal Porgali, Vítor Albiero, Jordan Ryda +2

This paper introduces a new large consent-driven dataset aimed at assisting in the evaluation of algorithmic bias and robustness of computer vision and audio speech models in regards to 11 attributes that are self-provided or labeled by trained annotators. The dataset includes 26,467 videos of 5,567 unique paid participants, with an average of almost 5 videos per person, recorded in Brazil, India, Indonesia, Mexico, Vietnam, Philippines, and the USA, representing diverse demographic characteristics. The participants agreed for their data to be used in assessing fairness of AI models and provided self-reported age, gender, language/dialect, disability status, physical adornments, physical attributes and geo-location information, while trained annotators labeled apparent skin tone using the Fitzpatrick Skin Type and Monk Skin Tone scales, and voice timbre. Annotators also labeled for different recording setups and per-second activity annotations.

Problems broadly known as algorithmic bias frequently occur in the context of complex socio-technical systems (STS), where observed biases may not be directly attributable to a single automated decision algorithm. As a first investigation of fairness in STS, we focus on the case of Wikipedia. We systematically review 75 papers describing different types of bias in Wikipedia, which we classify and relate to established notions of harm from algorithmic fairness research. By analysing causal relationships between the observed phenomena, we demonstrate the complexity of the socio-technical processes causing harm. Finally, we identify the normative expectations of fairness associated with the different problems and discuss the applicability of existing criteria proposed for machine learning-driven decision systems.

The applications of Artificial Intelligence (AI) methods especially machine learning techniques have increased in recent years. Classification algorithms have been successfully applied to different problems such as requirement classification. Although these algorithms have good performance, most of them cannot explain how they make a decision. Explainable Artificial Intelligence (XAI) is a set of new techniques that explain the predictions of machine learning algorithms. In this work, the applicability of XAI for software requirement classification is studied. An explainable software requirement classifier is presented using the LIME algorithm. The explainability of the proposed method is studied by applying it to the PROMISE software requirement dataset. The results show that XAI can help the analyst or requirement specifier to better understand why a specific requirement is classified as functional or non-functional. The important keywords for such decisions are identified and analyzed in detail. The experimental study shows that the XAI can be used to help analysts and requirement specifiers to better understand the predictions of the classifiers for categorizing software requirements. Also, the effect of the XAI on feature reduction is analyzed. The results showed that the XAI model has a positive role in feature analysis.

Constraint solving is an elementary way for verification of deep neural networks (DNN). In the domain of AI safety, a DNN might be modified in its structure and parameters for its repair or attack. For such situations, we propose the incremental DNN verification problem, which asks whether a safety property still holds after the DNN is modified. To solve the problem, we present an incremental satisfiability modulo theory (SMT) algorithm based on the Reluplex framework. We simulate the most important features of the configurations that infers the verification result of the searching branches in the old solving procedure (with respect to the original network), and heuristically check whether the proofs are still valid for the modified DNN. We implement our algorithm as an incremental solver called DeepInc, and exerimental results show that DeepInc is more efficient in most cases. For the cases that the property holds both before and after modification, the acceleration can be faster by several orders of magnitude, showing that DeepInc is outstanding in incrementally searching for counterexamples. Moreover, based on the framework, we propose the multi-objective DNN repair problem and give an algorithm based on our incremental SMT solving algorithm. Our repair method preserves more potential safety properties on the repaired DNNs compared with state-of-the-art.

Explainable Artificial Intelligence (XAI) techniques are frequently required by users in many AI systems with the goal of understanding complex models, their associated predictions, and gaining trust. While suitable for some specific tasks during development, their adoption by organisations to enhance trust in machine learning systems has unintended consequences. In this paper we discuss XAI's limitations in deployment and conclude that transparency alongside with rigorous validation are better suited to gaining trust in AI systems.

Decisions such as which movie to watch next, which song to listen to, or which product to buy online, are increasingly influenced by recommender systems and user models that incorporate information on users' past behaviours, preferences, and digitally created content. Machine learning models that enable recommendations and that are trained on user data may unintentionally leverage information on human characteristics that are considered vulnerabilities, such as depression, young age, or gambling addiction. The use of algorithmic decisions based on latent vulnerable state representations could be considered manipulative and could have a deteriorating impact on the condition of vulnerable individuals. In this paper, we are concerned with the problem of machine learning models inadvertently modelling vulnerabilities, and want to raise awareness for this issue to be considered in legislation and AI ethics. Hence, we define and describe common vulnerabilities, and illustrate cases where they are likely to play a role in algorithmic decision-making. We propose a set of requirements for methods to detect the potential for vulnerability modelling, detect whether vulnerable groups are treated differently by a model, and detect whether a model has created an internal representation of vulnerability. We conclude that explainable artificial intelligence methods may be necessary for detecting vulnerability exploitation by machine learning-based recommendation systems.

The recent release of ChatGPT has gained huge attention and discussion worldwide, with responsible AI being a key topic of discussion. How can we ensure that AI systems, including ChatGPT, are developed and adopted in a responsible way? To tackle the responsible AI challenges, various ethical principles have been released by governments, organisations, and companies. However, those principles are very abstract and not practical enough. Further, significant efforts have been put on algorithm-level solutions that only address a narrow set of principles, such as fairness and privacy. To fill the gap, we adopt a pattern-oriented responsible AI engineering approach and build a Responsible AI Pattern Catalogue to operationalise responsible AI from a system perspective. In this article, we first summarise the major challenges in operationalising responsible AI at scale and introduce how we use the Responsible AI Pattern Catalogue to address those challenges. We then examine the risks at each stage of the chatbot development process and recommend pattern-driven mitigations to evaluate the the usefulness of the Responsible AI Pattern Catalogue in a real-world setting.