Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race. To avoid disparate treatment, sensitive attributes should not be considered. On the other hand, in order to avoid disparate impact, sensitive attributes must be examined, e.g., in order to learn a fair model, or to check if a given model is fair. We introduce methods from secure multi-party computation which allow us to avoid both. By encrypting sensitive attributes, we show how an outcome-based fair model may be learned, checked, or have its outputs verified and held to account, without users revealing their sensitive attributes.

The latest techniques from Neural Networks and Support Vector Machines (SVM) are used to investigate geometric properties of Complete Intersection Calabi-Yau (CICY) threefolds, a class of manifolds that facilitate string model building. An advanced neural network classifier and SVM are employed to (1) learn Hodge numbers and report a remarkable improvement over previous efforts, (2) query for favourability, and (3) predict discrete symmetries, a highly imbalanced problem to which the Synthetic Minority Oversampling Technique (SMOTE) is applied to boost performance. In each case study, we employ a genetic algorithm to optimise the hyperparameters of the neural network. We demonstrate that our approach provides quick diagnostic tools capable of shortlisting quasi-realistic string models based on compactification over smooth CICYs and further supports the paradigm that classes of problems in algebraic geometry can be machine learned.

In machine learning, novelty detection is the task of identifying novel unseen data. During training, only samples from the normal class are available. Test samples are classified as normal or abnormal by assignment of a novelty score. Here we propose novelty detection methods based on training variational autoencoders (VAEs) on normal data. Since abnormal samples are not used during training, we define novelty metrics based on the (partially complementary) assumptions that the VAE is less capable of reconstructing abnormal samples well; that abnormal samples more strongly violate the VAE regularizer; and that abnormal samples differ from normal samples not only in input-feature space, but also in the VAE latent space and VAE output. These approaches, combined with various possibilities of using (e.g.~sampling) the probabilistic VAE to obtain scalar novelty scores, yield a large family of methods. We apply these methods to magnetic resonance imaging, namely to the detection of diffusion-space (\mbox{q-space}) abnormalities in diffusion MRI scans of multiple sclerosis patients, i.e.~to detect multiple sclerosis lesions without using any lesion labels for training. Many of our methods outperform previously proposed q-space novelty detection methods.

A golden eagle is seen flying over a wind turbine wind farm in Wyoming. Maybe not as many as some opponents would have you believe, but it's a problem for the renewable energy industry (along with improper siting in bird flight paths). Of course, coal-fired energy in the United States kills birds too. Eagles, also a symbol of America, hold a special place in the wildlife world. They're protected by federal law, and certainly worth protecting from the whooshing blades of wind turbines.

Cybercriminals are increasingly targeting public and internal web applications. Today, nearly half of all data breaches are caused by attacks targeting web application vulnerabilities. To protect your organization from such attacks, Web Application Firewalls (WAFs) are the gold standard. However, some organizations are reluctant to use these devices as they have a reputation for being very resource-intensive, especially when it comes to quickly addressing false positive detections in order to ensure that legitimate users and applications don't get blocked. The primary reason for the high number of false positive detections generated by most WAF solutions is the underlying core behavioral threat detection method being used.

Get your Minority Report or Skynet references ready, researchers at the University of Cambridge are working on a way to use AI and drone surveillance to spot violent behavior in crowds. The research paper even has a cool sci-fi name: Eye in the Sky. The project uses an inexpensive Parrot AR 2.0 drone to watch crowds of people from above. Then it uses AI to identify people in violent poses (the paper mentions strangling, punching, kicking, shooting and stabbing). It's important to note that the researchers didn't fly a drone around to detect real violence -- The Verge reports it shot its own video clips using volunteers.

This document contains the outcome of the first Human behaviour and machine intelligence (HUMAINT) workshop that took place 5-6 March 2018 in Barcelona, Spain. The workshop was organized in the context of a new research programme at the Centre for Advanced Studies, Joint Research Centre of the European Commission, which focuses on studying the potential impact of artificial intelligence on human behaviour. The workshop gathered an interdisciplinary group of experts to establish the state of the art research in the field and a list of future research challenges to be addressed on the topic of human and machine intelligence, algorithm's potential impact on human cognitive capabilities and decision making, and evaluation and regulation needs. The document is made of short position statements and identification of challenges provided by each expert, and incorporates the result of the discussions carried out during the workshop. In the conclusion section, we provide a list of emerging research topics and strategies to be addressed in the near future.

We revisit the importance of the individual units in Convolutional Neural Networks (CNNs) for visual recognition. By conducting unit ablation experiments on CNNs trained on large scale image datasets, we demonstrate that, though ablating any individual unit does not hurt overall classification accuracy, it does lead to significant damage on the accuracy of specific classes. This result shows that an individual unit is specialized to encode information relevant to a subset of classes. We compute the correlation between the accuracy drop under unit ablation and various attributes of an individual unit such as class selectivity and weight L1 norm. We confirm that unit attributes such as class selectivity are a poor predictor for impact on overall accuracy as found previously in recent work \cite{morcos2018importance}. However, our results show that class selectivity along with other attributes are good predictors of the importance of one unit to individual classes. We evaluate the impact of random rotation, batch normalization, and dropout to the importance of units to specific classes. Our results show that units with high selectivity play an important role in network classification power at the individual class level. Understanding and interpreting the behavior of these units is necessary and meaningful.

In this work we formally define the notions of adversarial perturbations, adversarial risk and adversarial training and analyze their properties. Our analysis provides several interesting insights into adversarial risk, adversarial training, and their relation to the classification risk, "traditional" training. We also show that adversarial training can result in models with better classification accuracy and can result in better explainable models than traditional training. Although adversarial training is computationally expensive, our results and insights suggest that one should prefer adversarial training over traditional risk minimization for learning complex models from data.

Dimensionality reduction is one of the key issues in the design of effective machine learning methods for automatic induction. In this work, we introduce recursive maxima hunting (RMH) for variable selection in classification problems with functional data. In this context, variable selection techniques are especially attractive because they reduce the dimensionality, facilitate the interpretation and can improve the accuracy of the predictive models. The method, which is a recursive extension of maxima hunting (MH), performs variable selection by identifying the maxima of a relevance function, which measures the strength of the correlation of the predictor functional variable with the class label. At each stage, the information associated with the selected variable is removed by subtracting the conditional expectation of the process. The results of an extensive empirical evaluation are used to illustrate that, in the problems investigated, RMH has comparable or higher predictive accuracy than the standard dimensionality reduction techniques, such as PCA and PLS, and state-of-the-art feature selection methods for functional data, such as maxima hunting.