The effective application of neural networks in the real-world relies on proficiently detecting out-of-distribution examples. Contemporary methods seek to model the distribution of feature activations in the training data for adequately distinguishing abnormalities, and the state-of-the-art method uses Gaussian distribution models. In this work, we present a novel approach that improves upon the state-of-the-art by leveraging an expressive density model based on normalizing flows. We introduce the residual flow, a novel flow architecture that learns the residual distribution from a base Gaussian distribution. Our model is general, and can be applied to any data that is approximately Gaussian. For novelty detection in image datasets, our approach provides a principled improvement over the state-of-the-art. Specifically, we demonstrate the effectiveness of our method in ResNet and DenseNet architectures trained on various image datasets. For example, on a ResNet trained on CIFAR-100 and evaluated on detection of out-of-distribution samples from the ImageNet dataset, holding the true positive rate (TPR) at $95\%$, we improve the true negative rate (TNR) from $56.7\%$ (current state-of-the-art) to $77.5\%$ (ours).

A classifier is only as good as the metric used to evaluate it. If you choose the wrong metric to evaluate your models, you are likely to choose a poor model, or in the worst case, be misled about the expected performance of your model. Choosing an appropriate metric is challenging generally in applied machine learning, but is particularly difficult for imbalanced classification problems. Firstly, because most of the standard metrics that are widely used assume a balanced class distribution, and because typically not all classes, and therefore, not all prediction errors, are equal for imbalanced classification. In this tutorial, you will discover metrics that you can use for imbalanced classification. Tour of Evaluation Metrics for Imbalanced Classification Photo by Travis Wise, some rights reserved.

A common mistake made by beginners is to apply machine learning algorithms to a problem without establishing a performance baseline. A performance baseline provides a minimum score above which a model is considered to have skill on the dataset. It also provides a point of relative improvement for all models evaluated on the dataset. A baseline can be established using a naive classifier, such as predicting one class label for all examples in the test dataset. Another common mistake made by beginners is using classification accuracy as a performance metric on problems that have an imbalanced class distribution.

Given the lack of evidence for new particle discoveries at the Large Hadron Collider (LHC), it is critical to broaden the search program. A variety of model-independent searches have been proposed, adding sensitivity to unexpected signals. There are generally two types of such searches: those that rely heavily on simulations and those that are entirely based on (unlabeled) data. This paper introduces a hybrid method that makes the best of both approaches. For potential signals that are resonant in one known feature, this new method first learns a parameterized reweighting function to morph a given simulation to match the data in sidebands. This function is then interpolated into the signal region and then the reweighted background-only simulation can be used for supervised learning as well as for background estimation. The background estimation from the reweighted simulation allows for non-trivial correlations between features used for classification and the resonant feature. A dijet search with jet substructure is used to illustrate the new method. Future applications of Simulation Assisted Likelihood-free Anomaly Detection (SALAD) include a variety of final states and potential combinations with other model-independent approaches.

We leverage recent breakthroughs in neural density estimation to propose a new unsupervised anomaly detection technique (ANODE). By estimating the probability density of the data in a signal region and in sidebands, and interpolating the latter into the signal region, a likelihood ratio of data vs. background can be constructed. This likelihood ratio is broadly sensitive to overdensities in the data that could be due to localized anomalies. In addition, a unique potential benefit of the ANODE method is that the background can be directly estimated using the learned densities. Finally, ANODE is robust against systematic differences between signal region and sidebands, giving it broader applicability than other methods. We demonstrate the power of this new approach using the LHC Olympics 2020 R\&D Dataset. We show how ANODE can enhance the significance of a dijet bump hunt by up to a factor of 7 with a 10\% accuracy on the background prediction. While the LHC is used as the recurring example, the methods developed here have a much broader applicability to anomaly detection in physics and beyond.

Mosquitoes are the only known vector of malaria, which leads to hundreds of thousands of deaths each year. Understanding the number and location of potential mosquito vectors is of paramount importance to aid the reduction of malaria transmission cases. In recent years, deep learning has become widely used for bioacoustic classification tasks. In order to enable further research applications in this field, we release a new dataset of mosquito audio recordings. With over a thousand contributors, we obtained 195,434 labels of two second duration, of which approximately 10 percent signify mosquito events. We present an example use of the dataset, in which we train a convolutional neural network on log-Mel features, showcasing the information content of the labels. We hope this will become a vital resource for those researching all aspects of malaria, and add to the existing audio datasets for bioacoustic detection and signal processing.

Algorithmic fairness in decision-making has been studied extensively in static settings where one-shot decisions are made on tasks such as classification. However, in practice most decision-making processes are of a sequential nature, where decisions made in the past may have an impact on future data. This is particularly the case when decisions affect the individuals or users generating the data used for future decisions. In this survey, we review existing literature on the fairness of data-driven sequential decision-making. We will focus on two types of sequential decisions: (1) past decisions have no impact on the underlying user population and thus no impact on future data; (2) past decisions have an impact on the underlying user population and therefore the future data, which can then impact future decisions. In each case the impact of various fairness interventions on the underlying population is examined.

Recent advancements in Artificial Intelligence (AI) have brought new capabilities to behavioural analysis (UEBA) for cyber-security consisting in the detection of hostile action based on the unusual nature of events observed on the Information System.In our previous work (presented at C\&ESAR 2018 and FIC 2019), we have associated deep neural networks auto-encoders for anomaly detection and graph-based events correlation to address major limitations in UEBA systems. This resulted in reduced false positive and false negative rates, improved alert explainability, while maintaining real-time performances and scalability. However, we did not address the natural evolution of behaviours through time, also known as concept drift. To maintain effective detection capabilities, an anomaly-based detection system must be continually trained, which opens a door to an adversary that can conduct the so-called "frog-boiling" attack by progressively distilling unnoticed attack traces inside the behavioural models until the complete attack is considered normal. In this paper, we present a solution to effectively mitigate this attack by improving the detection process and efficiently leveraging human expertise. We also present preliminary work on adversarial AI conducting deception attack, which, in term, will be used to help assess and improve the defense system. These defensive and offensive AI implement joint, continual and active learning, in a step that is necessary in assessing, validating and certifying AI-based defensive solutions.

Recently a team of researchers from Imperial College London and Google Health created a computer vision model intended to diagnose cases of breast cancer from X-rays. As CNN reports, the model was reportedly trained on X-rays of over 29,000 women, and when pitted against six radiologists the model managed to outperform the assessments of the doctors. Currently, the NHS uses the combined decisions of two doctors in order to diagnose breast cancer from X-rays. If the two doctors end up disagreeing, a third will be brought in to consult on the images. While the doctors had access to the medical records of the patients, the AI device only had the mammograms to base its decisions on.

Heterogeneity between training and testing data degrades reproducibility of a well-trained predictive algorithm. In modern applications, how to deploy a trained algorithm in a different domain is becoming an urgent question raised by many domain scientists. In this paper, we propose a reproducible bootstrap aggregating (Rbagging) method coupled with a new algorithm, the iterative nearest neighbor sampler (INNs), effectively drawing bootstrap samples from training data to mimic the distribution of the test data. Rbagging is a general ensemble framework that can be applied to most classifiers. We further propose Rbagging+ to effectively detect anomalous samples in the testing data. Our theoretical results show that the resamples based on Rbagging have the same distribution as the testing data. Moreover, under suitable assumptions, we further provide a general bound to control the test excess risk of the ensemble classifiers. The proposed method is compared with several other popular domain adaptation methods via extensive simulation studies and real applications including medical diagnosis and imaging classifications.