Research Papers

"Even if ..." -- Diverse Semifactual Explanations of Reject

André Artelt, Barbara Hammer

Machine learning based decision making systems applied in safety critical areas require reliable high certainty predictions. For this purpose, the system can be extended by an reject option which allows the system to reject inputs where only a prediction with an unacceptably low certainty would be possible. While being able to reject uncertain samples is important, it is also of importance to be able to explain why a particular sample was rejected. With the ongoing rise of eXplainable AI (XAI), a lot of explanation methodologies for machine learning based systems have been developed -- explaining reject options, however, is still a novel field where only very little prior work exists. In this work, we propose to explain rejects by semifactual explanations, an instance of example-based explanation methods, which them self have not been widely considered in the XAI community yet. We propose a conceptual modeling of semifactual explanations for arbitrary reject options and empirically evaluate a specific implementation on a conformal prediction based reject option.

Artificial Intelligence (AI) is becoming the corner stone of many systems used in our daily lives such as autonomous vehicles, healthcare systems, and unmanned aircraft systems. Machine Learning is a field of AI that enables systems to learn from data and make decisions on new data based on models to achieve a given goal. The stochastic nature of AI models makes verification and validation tasks challenging. Moreover, there are intrinsic biaises in AI models such as reproductibility bias, selection bias (e.g., races, genders, color), and reporting bias (i.e., results that do not reflect the reality). Increasingly, there is also a particular attention to the ethical, legal, and societal impacts of AI. AI systems are difficult to audit and certify because of their black-box nature. They also appear to be vulnerable to threats; AI systems can misbehave when untrusted data are given, making them insecure and unsafe. Governments, national and international organizations have proposed several principles to overcome these challenges but their applications in practice are limited and there are different interpretations in the principles that can bias implementations. In this paper, we examine trust in the context of AI-based systems to understand what it means for an AI system to be trustworthy and identify actions that need to be undertaken to ensure that AI systems are trustworthy. To achieve this goal, we first review existing approaches proposed for ensuring the trustworthiness of AI systems, in order to identify potential conceptual gaps in understanding what trustworthy AI is. Then, we suggest a trust (resp. zero-trust) model for AI and suggest a set of properties that should be satisfied to ensure the trustworthiness of AI systems.

Improving the performance and natural language explanations of deep learning algorithms is a priority for adoption by humans in the real world. In several domains, such as healthcare, such technology has significant potential to reduce the burden on humans by providing quality assistance at scale. However, current methods rely on the traditional pipeline of predicting labels from data, thus completely ignoring the process and guidelines used to obtain the labels. Furthermore, post hoc explanations on the data to label prediction using explainable AI (XAI) models, while satisfactory to computer scientists, leave much to be desired to the end-users due to lacking explanations of the process in terms of human-understandable concepts. We \textit{introduce}, \textit{formalize}, and \textit{develop} a novel Artificial Intelligence (A) paradigm -- Process Knowledge-infused Learning (PK-iL). PK-iL utilizes a structured process knowledge that explicitly explains the underlying prediction process that makes sense to end-users. The qualitative human evaluation confirms through a annotator agreement of 0.72, that humans are understand explanations for the predictions. PK-iL also performs competitively with the state-of-the-art (SOTA) baselines.

We investigate opinion dynamics and information spreading on networks under the influence of content filtering technologies. The filtering mechanism, present in many online social platforms, reduces individuals' exposure to disagreeing opinions, producing algorithmic bias. We derive evolution equations for global opinion variables in the presence of algorithmic bias, network community structure, noise (independent behavior of individuals), and pairwise or group interactions. We consider the case where the social platform shows a predilection for one opinion over its opposite, unbalancing the dynamics in favor of that opinion. We show that if the imbalance is strong enough, it may determine the final global opinion and the dynamical behavior of the population. We find a complex phase diagram including phases of coexistence, consensus, and polarization of opinions as possible final states of the model, with phase transitions of different order between them. The fixed point structure of the equations determines the dynamics to a large extent. We focus on the time needed for convergence and conclude that this quantity varies within a wide range, showing occasionally signatures of critical slowing down and meta-stability.

A novel explainable AI method called CLEAR Image is introduced in this paper. CLEAR Image is based on the view that a satisfactory explanation should be contrastive, counterfactual and measurable. CLEAR Image explains an image's classification probability by contrasting the image with a corresponding image generated automatically via adversarial learning. This enables both salient segmentation and perturbations that faithfully determine each segment's importance. CLEAR Image was successfully applied to a medical imaging case study where it outperformed methods such as Grad-CAM and LIME by an average of 27% using a novel pointing game metric. CLEAR Image excels in identifying cases of "causal overdetermination" where there are multiple patches in an image, any one of which is sufficient by itself to cause the classification probability to be close to one.

Cybersecurity is a domain where there is constant change in patterns of attack, and we need ways to make our Cybersecurity systems more adaptive to handle new attacks and categorize for appropriate action. We present a novel approach to handle the alarm flooding problem faced by Cybersecurity systems like security information and event management (SIEM) and intrusion detection (IDS). We apply a zero-shot learning method to machine learning (ML) by leveraging explanations for predictions of anomalies generated by a ML model. This approach has huge potential to auto detect alarm labels generated in SIEM and associate them with specific attack types. In this approach, without any prior knowledge of attack, we try to identify it, decipher the features that contribute to classification and try to bucketize the attack in a specific category - using explainable AI. Explanations give us measurable factors as to what features influence the prediction of a cyber-attack and to what degree. These explanations generated based on game-theory are used to allocate credit to specific features based on their influence on a specific prediction. Using this allocation of credit, we propose a novel zero-shot approach to categorize novel attacks into specific new classes based on feature influence. The resulting system demonstrated will get good at separating attack traffic from normal flow and auto-generate a label for attacks based on features that contribute to the attack. These auto-generated labels can be presented to SIEM analyst and are intuitive enough to figure out the nature of attack. We apply this approach to a network flow dataset and demonstrate results for specific attack types like ip sweep, denial of service, remote to local, etc. Paper was presented at the first Conference on Deployable AI at IIT-Madras in June 2021.

The potential presented by Artificial Intelligence (AI) for healthcare has long been recognised by the technical community. More recently, this potential has been recognised by policymakers, resulting in considerable public and private investment in the development of AI for healthcare across the globe. Despite this, excepting limited success stories, real-world implementation of AI systems into front-line healthcare has been limited. There are numerous reasons for this, but a main contributory factor is the lack of internationally accepted, or formalised, regulatory standards to assess AI safety and impact and effectiveness. This is a well-recognised problem with numerous ongoing research and policy projects to overcome it. Our intention here is to contribute to this problem-solving effort by seeking to set out a minimally viable framework for evaluating the safety, acceptability and efficacy of AI systems for healthcare. We do this by conducting a systematic search across Scopus, PubMed and Google Scholar to identify all the relevant literature published between January 1970 and November 2020 related to the evaluation of: output performance; efficacy; and real-world use of AI systems, and synthesising the key themes according to the stages of evaluation: pre-clinical (theoretical phase); exploratory phase; definitive phase; and post-market surveillance phase (monitoring). The result is a framework to guide AI system developers, policymakers, and regulators through a sufficient evaluation of an AI system designed for use in healthcare.

We consider the task of enforcing individual fairness in gradient boosting. Gradient boosting is a popular method for machine learning from tabular data, which arise often in applications where algorithmic fairness is a concern. At a high level, our approach is a functional gradient descent on a (distributionally) robust loss function that encodes our intuition of algorithmic fairness for the ML task at hand. Unlike prior approaches to individual fairness that only work with smooth ML models, our approach also works with non-smooth models such as decision trees. We show that our algorithm converges globally and generalizes. We also demonstrate the efficacy of our algorithm on three ML problems susceptible to algorithmic bias.

Exploring the Assessment List for Trustworthy AI in the Context of Advanced Driver-Assistance Systems

Markus Borg, Joshua Bronson, Linus Christensson +5

Artificial Intelligence (AI) is increasingly used in critical applications. Thus, the need for dependable AI systems is rapidly growing. In 2018, the European Commission appointed experts to a High-Level Expert Group on AI (AI-HLEG). AI-HLEG defined Trustworthy AI as 1) lawful, 2) ethical, and 3) robust and specified seven corresponding key requirements. To help development organizations, AI-HLEG recently published the Assessment List for Trustworthy AI (ALTAI). We present an illustrative case study from applying ALTAI to an ongoing development project of an Advanced Driver-Assistance System (ADAS) that relies on Machine Learning (ML). Our experience shows that ALTAI is largely applicable to ADAS development, but specific parts related to human agency and transparency can be disregarded. Moreover, bigger questions related to societal and environmental impact cannot be tackled by an ADAS supplier in isolation. We present how we plan to develop the ADAS to ensure ALTAI-compliance. Finally, we provide three recommendations for the next revision of ALTAI, i.e., life-cycle variants, domain-specific adaptations, and removed redundancy.

A Scalable Two Stage Approach to Computing Optimal Decision Sets

Alexey Ignatiev, Edward Lam, Peter J. Stuckey +1

Machine learning (ML) is ubiquitous in modern life. Since it is being deployed in technologies that affect our privacy and safety, it is often crucial to understand the reasoning behind its decisions, warranting the need for explainable AI. Rule-based models, such as decision trees, decision lists, and decision sets, are conventionally deemed to be the most interpretable. Recent work uses propositional satisfiability (SAT) solving (and its optimization variants) to generate minimum-size decision sets. Motivated by limited practical scalability of these earlier methods, this paper proposes a novel approach to learn minimum-size decision sets by enumerating individual rules of the target decision set independently of each other, and then solving a set cover problem to select a subset of rules. The approach makes use of modern maximum satisfiability and integer linear programming technologies. Experiments on a wide range of publicly available datasets demonstrate the advantage of the new approach over the state of the art in SAT-based decision set learning.

There appears to be a common agreement that ethical concerns are of high importance when it comes to systems equipped with some sort of Artificial Intelligence (AI). Demands for ethical AI are declared from all directions. As a response, in recent years, public bodies, governments, and universities have rushed in to provide a set of principles to be considered when AI based systems are designed and used. We have learned, however, that high-level principles do not turn easily into actionable advice for practitioners. Hence, also companies are publishing their own ethical guidelines to guide their AI development. This paper argues that AI software is still software and needs to be approached from the software development perspective. The software engineering paradigm has introduced maturity model thinking, which provides a roadmap for companies to improve their performance from the selected viewpoints known as the key capabilities. We want to voice out a call for action for the development of a maturity model for AI software. We wish to discuss whether the focus should be on AI ethics or, more broadly, the quality of an AI system, called a maturity model for the development of AI systems.

Remarkable success of modern image-based AI methods and the resulting interest in their applications in critical decision-making processes has led to a surge in efforts to make such intelligent systems transparent and explainable. The need for explainable AI does not stem only from ethical and moral grounds but also from stricter legislation around the world mandating clear and justifiable explanations of any decision taken or assisted by AI. Especially in the medical context where Computer-Aided Diagnosis can have a direct influence on the treatment and well-being of patients, transparency is of utmost importance for safe transition from lab research to real world clinical practice. This paper provides a comprehensive overview of current state-of-the-art in explaining and interpreting Deep Learning based algorithms in applications of medical research and diagnosis of diseases. We discuss early achievements in development of explainable AI for validation of known disease criteria, exploration of new potential biomarkers, as well as methods for the subsequent correction of AI models. Various explanation methods like visual, textual, post-hoc, ante-hoc, local and global have been thoroughly and critically analyzed. Subsequently, we also highlight some of the remaining challenges that stand in the way of practical applications of AI as a clinical decision support tool and provide recommendations for the direction of future research.