Deep Learning (DL) has made significant strides in various medical applications in recent years, achieving remarkable results. In the field of medical imaging, DL models can assist doctors in disease diagnosis by classifying pathologies in Chest X-ray images. However, training on new data to expand model capabilities and adapt to distribution shifts is a notable challenge these models face. Continual Learning (CL) has emerged as a solution to this challenge, enabling models to adapt to new data while retaining knowledge gained from previous experiences. Previous studies have analyzed the behavior of CL strategies in medical imaging regarding classification performance. However, when considering models that interact with sensitive information, such as in the medical domain, it is imperative to disaggregate the performance of socially salient groups. Indeed, DL algorithms can exhibit biases against certain sub-populations, leading to discrepancies in predictive performance across different groups identified by sensitive attributes such as age, race/ethnicity, sex/gender, and socioeconomic status. In this study, we go beyond the typical assessment of classification performance in CL and study bias evolution over successive tasks with domain-specific fairness metrics. Specifically, we evaluate the CL strategies using the well-known CheXpert (CXP) and ChestX-ray14 (NIH) datasets. We consider a class incremental scenario of five tasks with 12 pathologies. We evaluate the Replay, Learning without Forgetting (LwF), LwF Replay, and Pseudo-Label strategies. LwF and Pseudo-Label exhibit optimal classification performance, but when including fairness metrics in the evaluation, it is clear that Pseudo-Label is less biased. For this reason, this strategy should be preferred when considering real-world scenarios in which it is crucial to consider the fairness of the model.

Recently, ACM FAccT published an article by Kwegyir-Aggrey and colleagues (2023), critiquing the use of AUC ROC in predictive analytics in several domains. In this article, we offer a critique of that article. Specifically, we highlight technical inaccuracies in that paper's comparison of metrics, mis-specification of the interpretation and goals of AUC ROC, the article's use of the accuracy metric as a gold standard for comparison to AUC ROC, and the article's application of critiques solely to AUC ROC for concerns that would apply to the use of any metric. We conclude with a re-framing of the very valid concerns raised in that article, and discuss how the use of AUC ROC can remain a valid and appropriate practice in a well-informed predictive analytics approach taking those concerns into account. We conclude by discussing the combined use of multiple metrics, including machine learning bias metrics, and AUC ROC's place in such an approach. Like broccoli, AUC ROC is healthy, but also like broccoli, researchers and practitioners in our field shouldn't eat a diet of only AUC ROC.

Racial diversity has become increasingly discussed within the AI The utilization of racial and ethnic categories in the development and algorithmic fairness literature, yet little attention is focused on of datasets and models facilitates the inclusion and documentation justifying the choices of racial categories and understanding how of diverse perspectives. Racial and ethnic categories are especially people are racialized into these chosen racial categories. Even less crucial for datasets and models in which race and ethnicity attention is given to how racial categories shift and how the racialization serve as relevant factors, may act as confounding variables, or enable process changes depending on the context of a dataset or the ability to audit for fairness using race and ethnicity for model. An unclear understanding of who comprises the racial categories fairness purposes. For example, understanding the racial and/or chosen and how people are racialized into these categories ethnic target of hate speech is crucial for understanding the impact can lead to varying interpretations of these categories. These varying of hate speech, as hate speech can differ based on the race interpretations can lead to harm when the understanding of and/or ethnicity of the target[48]. Similarly, in health, race is correlated racial categories and the racialization process is misaligned from with health outcomes[6], and knowledge of a patient's race the actual racialization process and racial categories used. Harm and ethnicity can help contextualize the patient's experience and can also arise if the racialization process and racial categories used health history[53]. In algorithmic fairness settings, knowledge of are irrelevant ordonot exist inthecontext they areapplied.

Entity matching is one the earliest tasks that occur in the big data pipeline and is alarmingly exposed to unintentional biases that affect the quality of data. Identifying and mitigating the biases that exist in the data or are introduced by the matcher at this stage can contribute to promoting fairness in downstream tasks. This demonstration showcases FairEM360, a framework for 1) auditing the output of entity matchers across a wide range of fairness measures and paradigms, 2) providing potential explanations for the underlying reasons for unfairness, and 3) providing resolutions for the unfairness issues through an exploratory process with human-in-the-loop feedback, utilizing an ensemble of matchers. We aspire for FairEM360 to contribute to the prioritization of fairness as a key consideration in the evaluation of EM pipelines.

Language models trained on internet-scale data sets have shown an impressive ability to solve problems in Natural Language Processing and Computer Vision. However, experience is showing that these models are frequently brittle in unexpected ways, and require significant scaffolding to ensure that they operate correctly in the larger systems that comprise "language-model agents." In this paper, we argue that behavior trees provide a unifying framework for combining language models with classical AI and traditional programming. We introduce Dendron, a Python library for programming language model agents using behavior trees. We demonstrate the approach embodied by Dendron in three case studies: building a chat agent, a camera-based infrastructure inspection agent for use on a mobile robot or vehicle, and an agent that has been built to satisfy safety constraints that it did not receive through instruction tuning or RLHF.

While reinforcement learning (RL) algorithms have been successfully applied across numerous sequential decision-making problems, their generalization to unforeseen testing environments remains a significant concern. In this paper, we study the problem of out-of-distribution (OOD) detection in RL, which focuses on identifying situations at test time that RL agents have not encountered in their training environments. We first propose a clarification of terminology for OOD detection in RL, which aligns it with the literature from other machine learning domains. We then present new benchmark scenarios for OOD detection, which introduce anomalies with temporal autocorrelation into different components of the agent-environment loop. We argue that such scenarios have been understudied in the current literature, despite their relevance to real-world situations. Confirming our theoretical predictions, our experimental results suggest that state-of-the-art OOD detectors are not able to identify such anomalies. To address this problem, we propose a novel method for OOD detection, which we call DEXTER (Detection via Extraction of Time Series Representations). By treating environment observations as time series data, DEXTER extracts salient time series features, and then leverages an ensemble of isolation forest algorithms to detect anomalies. We find that DEXTER can reliably identify anomalies across benchmark scenarios, exhibiting superior performance compared to both state-of-the-art OOD detectors and high-dimensional changepoint detectors adopted from statistics.

One key task in environmental science is to map environmental variables continuously in space or even in space and time. Machine learning algorithms are frequently used to learn from local field observations to make spatial predictions by estimating the value of the variable of interest in places where it has not been measured. However, the application of machine learning strategies for spatial mapping involves additional challenges compared to "non-spatial" prediction tasks that often originate from spatial autocorrelation and from training data that are not independent and identically distributed. In the past few years, we developed a number of methods to support the application of machine learning for spatial data which involves the development of suitable cross-validation strategies for performance assessment and model selection, spatial feature selection, and methods to assess the area of applicability of the trained models. The intention of the CAST package is to support the application of machine learning strategies for predictive mapping by implementing such methods and making them available for easy integration into modelling workflows. Here we introduce the CAST package and its core functionalities. At the case study of mapping plant species richness, we will go through the different steps of the modelling workflow and show how CAST can be used to support more reliable spatial predictions.

Motivated by modern data forms such as images and multi-view data, the multi-attribute graphical model aims to explore the conditional independence structure among vectors. Under the Gaussian assumption, the conditional independence between vectors is characterized by blockwise zeros in the precision matrix. To relax the restrictive Gaussian assumption, in this paper, we introduce a novel semiparametric multi-attribute graphical model based on a new copula named Cyclically Monotone Copula. This new copula treats the distribution of the node vectors as multivariate marginals and transforms them into Gaussian distributions based on the optimal transport theory. Since the model allows the node vectors to have arbitrary continuous distributions, it is more flexible than the classical Gaussian copula method that performs coordinatewise Gaussianization. We establish the concentration inequalities of the estimated covariance matrices and provide sufficient conditions for selection consistency of the group graphical lasso estimator. For the setting with high-dimensional attributes, a {Projected Cyclically Monotone Copula} model is proposed to address the curse of dimensionality issue that arises from solving high-dimensional optimal transport problems. Numerical results based on synthetic and real data show the efficiency and flexibility of our methods.

Students have submitted more than 22 million papers that may have used generative AI in the past year, new data released by plagiarism detection company Turnitin shows. A year ago, Turnitin rolled out an AI writing detection tool that was trained on its trove of papers written by students as well as other AI-generated texts. Since then, more than 200 million papers have been reviewed by the detector, predominantly written by high school and college students. Turnitin found that 11 percent may contain AI-written language in 20 percent of its content, with 3 percent of the total papers reviewed getting flagged for having 80 percent or more AI writing. Turnitin says its detector has a false positive rate of less than 1 percent when analyzing full documents.

In this work, we conduct a comprehensive study on the robustness of domain generation algorithm (DGA) classifiers. We implement 32 white-box attacks, 19 of which are very effective and induce a false-negative rate (FNR) of $\approx$ 100\% on unhardened classifiers. To defend the classifiers, we evaluate different hardening approaches and propose a novel training scheme that leverages adversarial latent space vectors and discretized adversarial domains to significantly improve robustness. In our study, we highlight a pitfall to avoid when hardening classifiers and uncover training biases that can be easily exploited by attackers to bypass detection, but which can be mitigated by adversarial training (AT). In our study, we do not observe any trade-off between robustness and performance, on the contrary, hardening improves a classifier's detection performance for known and unknown DGAs. We implement all attacks and defenses discussed in this paper as a standalone library, which we make publicly available to facilitate hardening of DGA classifiers: https://gitlab.com/rwth-itsec/robust-dga-detection