Research Papers

In this work, CT-xCOV, an explainable framework for COVID-19 diagnosis using Deep Learning (DL) on CT-scans is developed. CT-xCOV adopts an end-to-end approach from lung segmentation to COVID-19 detection and explanations of the detection model's prediction. For lung segmentation, we used the well-known U-Net model. For COVID-19 detection, we compared three different CNN architectures: a standard CNN, ResNet50, and DenseNet121. After the detection, visual and textual explanations are provided. For visual explanations, we applied three different XAI techniques, namely, Grad-Cam, Integrated Gradient (IG), and LIME. Textual explanations are added by computing the percentage of infection by lungs. To assess the performance of the used XAI techniques, we propose a ground-truth-based evaluation method, measuring the similarity between the visualization outputs and the ground-truth infections. The performed experiments show that the applied DL models achieved good results. The U-Net segmentation model achieved a high Dice coefficient (98%). The performance of our proposed classification model (standard CNN) was validated using 5-fold cross-validation (acc of 98.40% and f1-score 98.23%). Lastly, the results of the comparison of XAI techniques show that Grad-Cam gives the best explanations compared to LIME and IG, by achieving a Dice coefficient of 55%, on COVID-19 positive scans, compared to 29% and 24% obtained by IG and LIME respectively. The code and the dataset used in this paper are available in the GitHub repository [1].

Liver diseases pose a significant global health burden, impacting many individuals and having substantial economic and social consequences. Rising liver problems are considered a fatal disease in many countries, such as Egypt and Moldova. This study aims to develop a diagnosis and treatment model for liver disease using Basic Formal Ontology (BFO), Patient Clinical Data (PCD) ontology, and detection rules derived from a decision tree algorithm. For the development of the ontology, the National Viral Hepatitis Control Program (NVHCP) guidelines were used, which made the ontology more accurate and reliable. The Apache Jena framework uses batch processing to detect events based on these rules. Based on the event detected, queries can be directly processed using SPARQL. We convert these Decision Tree (DT) and medical guidelines-based rules into Semantic Web Rule Language (SWRL) to operationalize the ontology. Using this SWRL in the ontology to predict different types of liver disease with the help of the Pellet and Drools inference engines in Protege Tools, a total of 615 records were taken from different liver diseases. After inferring the rules, the result can be generated for the patient according to the rules, and other patient-related details, along with different precautionary suggestions, can be obtained based on these results. These rules can make suggestions more accurate with the help of Explainable Artificial Intelligence (XAI) with open API-based suggestions. When the patient has prescribed a medical test, the model accommodates this result using optical character recognition (OCR), and the same process applies when the patient has prescribed a further medical suggestion according to the test report. These models combine to form a comprehensive Decision Support System (DSS) for the diagnosis of liver disease.

Advancing Post Hoc Case Based Explanation with Feature Highlighting

Eoin Kenny, Eoin Delaney, Mark Keane

Explainable AI (XAI) has been proposed as a valuable tool to assist in downstream tasks involving human and AI collaboration. Perhaps the most psychologically valid XAI techniques are case based approaches which display 'whole' exemplars to explain the predictions of black box AI systems. However, for such post hoc XAI methods dealing with images, there has been no attempt to improve their scope by using multiple clear feature 'parts' of the images to explain the predictions while linking back to relevant cases in the training data, thus allowing for more comprehensive explanations that are faithful to the underlying model. Here, we address this gap by proposing two general algorithms (latent and super pixel based) which can isolate multiple clear feature parts in a test image, and then connect them to the explanatory cases found in the training data, before testing their effectiveness in a carefully designed user study. Results demonstrate that the proposed approach appropriately calibrates a users feelings of 'correctness' for ambiguous classifications in real world data on the ImageNet dataset, an effect which does not happen when just showing the explanation without feature highlighting.

Text classification aims to effectively categorize documents into pre-defined categories. Traditional methods for text classification often rely on large amounts of manually annotated training data, making the process time-consuming and labor-intensive. To address this issue, recent studies have focused on weakly-supervised and extremely weakly-supervised settings, which require minimal or no human annotation, respectively. In previous methods of weakly supervised text classification, pseudo-training data is generated by assigning pseudo-labels to documents based on their alignment (e.g., keyword matching) with specific classes. However, these methods ignore the importance of incorporating the explanations of the generated pseudo-labels, or saliency of individual words, as additional guidance during the text classification training process. To address this limitation, we propose XAI-CLASS, a novel explanation-enhanced extremely weakly-supervised text classification method that incorporates word saliency prediction as an auxiliary task. XAI-CLASS begins by employing a multi-round question-answering process to generate pseudo-training data that promotes the mutual enhancement of class labels and corresponding explanation word generation. This pseudo-training data is then used to train a multi-task framework that simultaneously learns both text classification and word saliency prediction. Extensive experiments on several weakly-supervised text classification datasets show that XAI-CLASS outperforms other weakly-supervised text classification methods significantly. Moreover, experiments demonstrate that XAI-CLASS enhances both model performance and explainability.

Artificial Intelligence (AI) has made its way into various scientific fields, providing astonishing improvements over existing algorithms for a wide variety of tasks. In recent years, there have been severe concerns over the trustworthiness of AI technologies. The scientific community has focused on the development of trustworthy AI algorithms. However, machine and deep learning algorithms, popular in the AI community today, depend heavily on the data used during their development. These learning algorithms identify patterns in the data, learning the behavioral objective. Any flaws in the data have the potential to translate directly into algorithms. In this study, we discuss the importance of Responsible Machine Learning Datasets and propose a framework to evaluate the datasets through a responsible rubric. While existing work focuses on the post-hoc evaluation of algorithms for their trustworthiness, we provide a framework that considers the data component separately to understand its role in the algorithm. We discuss responsible datasets through the lens of fairness, privacy, and regulatory compliance and provide recommendations for constructing future datasets. After surveying over 100 datasets, we use 60 datasets for analysis and demonstrate that none of these datasets is immune to issues of fairness, privacy preservation, and regulatory compliance. We provide modifications to the ``datasheets for datasets" with important additions for improved dataset documentation. With governments around the world regularizing data protection laws, the method for the creation of datasets in the scientific community requires revision. We believe this study is timely and relevant in today's era of AI.

Transparent Anomaly Detection via Concept-based Explanations

Laya Rafiee Sevyeri, Ivaxi Sheth, Farhood Farahnak +2

Advancements in deep learning techniques have given a boost to the performance of anomaly detection. However, real-world and safety-critical applications demand a level of transparency and reasoning beyond accuracy. The task of anomaly detection (AD) focuses on finding whether a given sample follows the learned distribution. Existing methods lack the ability to reason with clear explanations for their outcomes. Hence to overcome this challenge, we propose Transparent {A}nomaly Detection {C}oncept {E}xplanations (ACE). ACE is able to provide human interpretable explanations in the form of concepts along with anomaly prediction. To the best of our knowledge, this is the first paper that proposes interpretable by-design anomaly detection. In addition to promoting transparency in AD, it allows for effective human-model interaction. Our proposed model shows either higher or comparable results to black-box uninterpretable models. We validate the performance of ACE across three realistic datasets - bird classification on CUB-200-2011, challenging histopathology slide image classification on TIL-WSI-TCGA, and gender classification on CelebA. We further demonstrate that our concept learning paradigm can be seamlessly integrated with other classification-based AD methods.

Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for predictions is crucial in advancing fair and trustworthy AI. While several promising methods for removing attribute bias in neural networks have been proposed, their limitations remain under-explored. In this work, we mathematically and empirically reveal an important limitation of attribute bias removal methods in presence of strong bias. Specifically, we derive a general non-vacuous information-theoretical upper bound on the performance of any attribute bias removal method in terms of the bias strength. We provide extensive experiments on synthetic, image, and census datasets to verify the theoretical bound and its consequences in practice. Our findings show that existing attribute bias removal methods are effective only when the inherent bias in the dataset is relatively weak, thus cautioning against the use of these methods in smaller datasets where strong attribute bias can occur, and advocating the need for methods that can overcome this limitation.

Visual inspection tasks often require humans to cooperate with AI-based image classifiers. To enhance this cooperation, explainable artificial intelligence (XAI) can highlight those image areas that have contributed to an AI decision. However, the literature on visual cueing suggests that such XAI support might come with costs of its own. To better understand how the benefits and cost of XAI depend on the accuracy of AI classifications and XAI highlights, we conducted two experiments that simulated visual quality control in a chocolate factory. Participants had to decide whether chocolate moulds contained faulty bars or not, and were always informed whether the AI had classified the mould as faulty or not. In half of the experiment, they saw additional XAI highlights that justified this classification. While XAI speeded up performance, its effects on error rates were highly dependent on (X)AI accuracy. XAI benefits were observed when the system correctly detected and highlighted the fault, but XAI costs were evident for misplaced highlights that marked an intact area while the actual fault was located elsewhere. Eye movement analyses indicated that participants spent less time searching the rest of the mould and thus looked at the fault less often. However, we also observed large interindividual differences. Taken together, the results suggest that despite its potentials, XAI can discourage people from investing effort into their own information analysis.

Refutation of Shapley Values for XAI -- Additional Evidence

Xuanxiang Huang, Joao Marques-Silva

Recent work demonstrated the inadequacy of Shapley values for explainable artificial intelligence (XAI). Although to disprove a theory a single counterexample suffices, a possible criticism of earlier work is that the focus was solely on Boolean classifiers. To address such possible criticism, this paper demonstrates the inadequacy of Shapley values for families of classifiers where features are not boolean, but also for families of classifiers for which multiple classes can be picked. Furthermore, the paper shows that the features changed in any minimal $l_0$ distance adversarial examples do not include irrelevant features, thus offering further arguments regarding the inadequacy of Shapley values for XAI.

With large chess-playing neural network models like AlphaZero contesting the state of the art within the world of computerised chess, two challenges present themselves: The question of how to explain the domain knowledge internalised by such models, and the problem that such models are not made openly available. This work presents the re-implementation of the concept detection methodology applied to AlphaZero in McGrath et al. (2022), by using large, open-source chess models with comparable performance. We obtain results similar to those achieved on AlphaZero, while relying solely on open-source resources. We also present a novel explainable AI (XAI) method, which is guaranteed to highlight exhaustively and exclusively the information used by the explained model. This method generates visual explanations tailored to domains characterised by discrete input spaces, as is the case for chess. Our presented method has the desirable property of controlling the information flow between any input vector and the given model, which in turn provides strict guarantees regarding what information is used by the trained model during inference. We demonstrate the viability of our method by applying it to standard 8x8 chess, using large open-source chess models.

Artificial intelligence (AI) promises immense benefits across sectors, yet also poses risks from dual-use potentials, biases, and unintended behaviors. This paper reviews emerging issues with opaque and uncontrollable AI systems and proposes an integrative framework called violet teaming to develop reliable and responsible AI. Violet teaming combines adversarial vulnerability probing (red teaming) with solutions for safety and security (blue teaming) while prioritizing ethics and social benefit. It emerged from AI safety research to manage risks proactively by design. The paper traces the evolution of red, blue, and purple teaming toward violet teaming, and then discusses applying violet techniques to address biosecurity risks of AI in biotechnology. Additional sections review key perspectives across law, ethics, cybersecurity, macrostrategy, and industry best practices essential for operationalizing responsible AI through holistic technical and social considerations. Violet teaming provides both philosophy and method for steering AI trajectories toward societal good. With conscience and wisdom, the extraordinary capabilities of AI can enrich humanity. But without adequate precaution, the risks could prove catastrophic. Violet teaming aims to empower moral technology for the common welfare.

This research aims develop an Explainable Artificial Intelligence (XAI) framework to facilitate human-understandable solutions for tool wear prediction during turning. A random forest algorithm was used as the supervised Machine Learning (ML) classifier for training and binary classification using acceleration, acoustics, temperature, and spindle speed during the orthogonal tube turning process as input features. The ML classifier was used to predict the condition of the tool after the cutting process, which was determined in a binary class form indicating if the cutting tool was available or failed. After the training process, the Shapley criterion was used to explain the predictions of the trained ML classifier. Specifically, the significance of each input feature in the decision-making and classification was identified to explain the reasoning of the ML classifier predictions. After implementing the Shapley criterion on all testing datasets, the tool temperature was identified as the most significant feature in determining the classification of available versus failed cutting tools. Hence, this research demonstrates capability of XAI to provide machining operators the ability to diagnose and understand complex ML classifiers in prediction of tool wear.