Jinsook Lee, Chris Brooks, Renzhe Yu, Rene Kizilcec To measure bias, we encourage teams to consider using AUC Gap: the absolute difference between the highest and lowest test AUC for subgroups (e.g., gender, race, SES, prior knowledge). It is agnostic to the AI/ML algorithm used and it captures the disparity in model performance for any number of subgroups, which enables non-binary fairness assessments such as for intersectional identity groups. The teams use a wide range of AI/ML models in pursuit of a common goal of doubling math achievement in low-income middle schools. Ensuring that the models, which are trained on datasets collected in many different contexts, do not introduce or amplify biases is important for achieving the goal. We offer here a versatile and easy-to-compute measure of model bias for all teams in order to create a common benchmark and an analytical basis for sharing what strategies have worked for different teams.

We propose FLARE, the first fingerprinting mechanism to verify whether a suspected Deep Reinforcement Learning (DRL) policy is an illegitimate copy of another (victim) policy. We first show that it is possible to find non-transferable, universal adversarial masks, i.e., perturbations, to generate adversarial examples that can successfully transfer from a victim policy to its modified versions but not to independently trained policies. FLARE employs these masks as fingerprints to verify the true ownership of stolen DRL policies by measuring an action agreement value over states perturbed by such masks. Our empirical evaluations show that FLARE is effective (100% action agreement on stolen copies) and does not falsely accuse independent policies (no false positives). FLARE is also robust to model modification attacks and cannot be easily evaded by more informed adversaries without negatively impacting agent performance. We also show that not all universal adversarial masks are suitable candidates for fingerprints due to the inherent characteristics of DRL policies. The spatio-temporal dynamics of DRL problems and sequential decision-making process make characterizing the decision boundary of DRL policies more difficult, as well as searching for universal masks that capture the geometry of it.

The problem of revealing botnet activity through Domain Generation Algorithm (DGA) detection seems to be solved, considering that available deep learning classifiers achieve accuracies of over 99.9%. However, these classifiers provide a false sense of security as they are heavily biased and allow for trivial detection bypass. In this work, we leverage explainable artificial intelligence (XAI) methods to analyze the reasoning of deep learning classifiers and to systematically reveal such biases. We show that eliminating these biases from DGA classifiers considerably deteriorates their performance. Nevertheless we are able to design a context-aware detection system that is free of the identified biases and maintains the detection rate of state-of-the art deep learning classifiers. In this context, we propose a visual analysis system that helps to better understand a classifier's reasoning, thereby increasing trust in and transparency of detection methods and facilitating decision-making.

The out-of-distribution (OOD) problem generally arises when neural networks encounter data that significantly deviates from the training data distribution, i.e., in-distribution (InD). In this paper, we study the OOD problem from a neuron activation view. We first formulate neuron activation states by considering both the neuron output and its influence on model decisions. Then, to characterize the relationship between neurons and OOD issues, we introduce the \textit{neuron activation coverage} (NAC) -- a simple measure for neuron behaviors under InD data. Leveraging our NAC, we show that 1) InD and OOD inputs can be largely separated based on the neuron behavior, which significantly eases the OOD detection problem and beats the 21 previous methods over three benchmarks (CIFAR-10, CIFAR-100, and ImageNet-1K). 2) a positive correlation between NAC and model generalization ability consistently holds across architectures and datasets, which enables a NAC-based criterion for evaluating model robustness. Compared to prevalent InD validation criteria, we show that NAC not only can select more robust models, but also has a stronger correlation with OOD test performance.

Artificial Intelligence (AI) and machine learning have been increasingly adopted for travel demand forecasting. The AI-based travel demand forecasting models, though generate accurate predictions, may produce prediction biases and raise fairness issues. Using such biased models for decision-making may lead to transportation policies that exacerbate social inequalities. However, limited studies have been focused on addressing the fairness issues of these models. Therefore, in this study, we propose a novel methodology to develop fairness-aware, highly-accurate travel demand forecasting models. Particularly, the proposed methodology can enhance the fairness of AI models for multiple protected attributes (such as race and income) simultaneously. Specifically, we introduce a new fairness regularization term, which is explicitly designed to measure the correlation between prediction accuracy and multiple protected attributes, into the loss function of the travel demand forecasting model. We conduct two case studies to evaluate the performance of the proposed methodology using real-world ridesourcing-trip data in Chicago, IL and Austin, TX, respectively. Results highlight that our proposed methodology can effectively enhance fairness for multiple protected attributes while preserving prediction accuracy. Additionally, we have compared our methodology with three state-of-the-art methods that adopt the regularization term approach, and the results demonstrate that our approach significantly outperforms them in both preserving prediction accuracy and enhancing fairness. This study can provide transportation professionals with a new tool to achieve fair and accurate travel demand forecasting.

This tutorial demonstrates workflows to incorporate text data into actuarial classification and regression tasks. The main focus is on methods employing transformer-based models. A dataset of car accident descriptions with an average length of 400 words, available in English and German, and a dataset with short property insurance claims descriptions are used to demonstrate these techniques. The case studies tackle challenges related to a multi-lingual setting and long input sequences. They also show ways to interpret model output, to assess and improve model performance, by fine-tuning the models to the domain of application or to a specific prediction task. Finally, the tutorial provides practical approaches to handle classification tasks in situations with no or only few labeled data, including but not limited to ChatGPT. The results achieved by using the language-understanding skills of off-the-shelf natural language processing (NLP) models with only minimal pre-processing and fine-tuning clearly demonstrate the power of transfer learning for practical applications.

This work investigates the predictive potential of bipolar electroencephalogram (EEG) recordings towards efficient prediction of poor neurological outcomes. A retrospective design using a hybrid deep learning approach is utilized to optimize an objective function aiming for high specificity, i.e., true positive rate (TPR) with reduced false positives (< 0.05). A multi-channel EEG array of 18 bipolar channel pairs from a randomly selected 5-minute segment in an hour is kept. In order to determine the outcome prediction, a combination of a feature encoder with 1-D convolutional layers, learnable position encoding, a context network with attention mechanisms, and finally, a regressor and classifier blocks are used. The feature encoder extricates local temporal and spatial features, while the following position encoding and attention mechanisms attempt to capture global temporal dependencies. Results: The proposed framework by our team, OUS IVS, when validated on the challenge hidden validation data, exhibited a score of 0.57.

Explicit finite-sample statistical guarantees on model performance are an important ingredient in responsible machine learning. Previous work has focused mainly on bounding either the expected loss of a predictor or the probability that an individual prediction will incur a loss value in a specified range. However, for many high-stakes applications, it is crucial to understand and control the dispersion of a loss distribution, or the extent to which different members of a population experience unequal effects of algorithmic decisions. We initiate the study of distribution-free control of statistical dispersion measures with societal implications and propose a simple yet flexible framework that allows us to handle a much richer class of statistical functionals beyond previous work. Our methods are verified through experiments in toxic comment detection, medical imaging, and film recommendation.

In the last decade, developments in tropical geometry have provided a number of uses directly applicable to problems in statistical learning. The TML package is the first R package which contains a comprehensive set of tools and methods used for basic computations related to tropical convexity, visualization of tropically convex sets, as well as supervised and unsupervised learning models using the tropical metric under the max-plus algebra over the tropical projective torus. Primarily, the TML package employs a Hit and Run Markov chain Monte Carlo sampler in conjunction with the tropical metric as its main tool for statistical inference. In addition to basic computation and various applications of the tropical HAR sampler, we also focus on several supervised and unsupervised methods incorporated in the TML package including tropical principal component analysis, tropical logistic regression and tropical kernel density estimation.

The widely observed 'benign overfitting phenomenon' in the neural network literature raises the challenge to the 'bias-variance trade-off' doctrine in the statistical learning theory. Since the generalization ability of the 'lazy trained' over-parametrized neural network can be well approximated by that of the neural tangent kernel regression, the curve of the excess risk (namely, the learning curve) of kernel ridge regression attracts increasing attention recently. However, most recent arguments on the learning curve are heuristic and are based on the 'Gaussian design' assumption. In this paper, under mild and more realistic assumptions, we rigorously provide a full characterization of the learning curve: elaborating the effect and the interplay of the choice of the regularization parameter, the source condition and the noise. In particular, our results suggest that the 'benign overfitting phenomenon' exists in very wide neural networks only when the noise level is small.