Learning-enabled controllers used in cyber-physical systems (CPS) are known to be susceptible to adversarial attacks. Such attacks manifest as perturbations to the states generated by the controller's environment in response to its actions. We consider state perturbations that encompass a wide variety of adversarial attacks and describe an attack scheme for discovering adversarial states. To be useful, these attacks need to be natural, yielding states in which the controller can be reasonably expected to generate a meaningful response. We consider shield-based defenses as a means to improve controller robustness in the face of such perturbations. Our defense strategy allows us to treat the controller and environment as black-boxes with unknown dynamics. We provide a two-stage approach to construct this defense and show its effectiveness through a range of experiments on realistic continuous control domains such as the navigation control-loop of an F16 aircraft and the motion control system of humanoid robots.

Generalized additive models (GAMs) have become a leading model class for data bias discovery and model auditing. However, there are a variety of algorithms for training GAMs, and these do not always learn the same things. Statisticians originally used splines to train GAMs, but more recently GAMs are being trained with boosted decision trees. It is unclear which GAM model(s) to believe, particularly when their explanations are contradictory. In this paper, we investigate a variety of different GAM algorithms both qualitatively and quantitatively on real and simulated datasets. Our results suggest that inductive bias plays a crucial role in model explanations and tree-based GAMs are to be recommended for the kinds of problems and dataset sizes we worked with.

Financial implications of written reviews provide great incentives for businesses to pay fraudsters to write or use bots to generate fraud reviews. The promising performance of Deep Neural Networks (DNNs) in text classification, has attracted research to use them for fraud review detection. However, the lack of trusted labeled data has limited the performance of the current solutions in detecting fraud reviews. Unsupervised and semi-supervised methods are among the most applicable methods to deal with the data scarcity problem. Generative Adversarial Network (GAN) as a semi-supervised method has demonstrated to be effective for data augmentation purposes. The state-of-the-art solution utilizes GAN to overcome the data limitation problem. However, it fails to incorporate the behavioral clues in both fraud generation and detection. Besides, the state-of-the-art approach suffers from a common limitation in the training convergence of the GAN, slowing down the training procedure. In this work, we propose a regularised GAN for fraud review detection that makes use of both review text and review rating scores. Scores are incorporated through Information Gain Maximization in to the loss function for two reasons. One is to generate near-authentic and more human like score-correlated reviews. The other is to improve the stability of the GAN. Experimental results have shown better convergence of the regulated GAN. In addition, the scores are also used in combination with word embeddings of review text as input for the discriminators for better performance. Results show that the proposed framework relatively outperformed existing state-of-the-art framework; namely FakeGAN; in terms of AP by 7%, and 5% on the Yelp and TripAdvisor datasets, respectively.

We propose a new framework for robust binary classification, with Deep Neural Networks, based on a hinge regularization of the Kantorovich-Rubinstein dual formulation for the estimation of the Wasserstein distance. The robustness of the approach is guaranteed by the strict Lipschitz constraint on functions required by the optimization problem and direct interpretation of the loss in terms of adversarial robustness. We prove that this classification formulation has a solution, and is still the dual formulation of an optimal transportation problem. We also establish the geometrical properties of this optimal solution. We summarize state-of-the-art methods to enforce Lipschitz constraints on neural networks and we propose new ones for convolutional networks (associated with an open source library for this purpose). The experiments show that the approach provides the expected guarantees in terms of robustness without any significant accuracy drop. The results also suggest that adversarial attacks on the proposed models visibly and meaningfully change the input, and can thus serve as an explanation for the classification.

In this work we aimed at comparing our findings in depression detection task with methodologies applied in present literature. Previously we showed that when electrophysiological signal (in this case electroencephalogram, EEG) is characterized by nonlinear measures, any of seven most popular classifiers yields high accuracy on the task. Following every step we done in this process we compare it with other researchers' practice and comment on other findings mainly from analysis of electrical signals or nonlinear analysis showing what would be optimal for further research. We focused on discussing various mistakes and differences that could potentially lead to unwarranted optimism and other misinterpretation of results. In Conclusion we summarize recommendation for future research in order to be applicable in clinical practice. Introduction Current clinical psychiatry is lacking objective biochemical or electrophysiological tests used for diagnosis unlike other medical disciplines. To diagnose depression, clinician will typically rely on the self-report from the patient and his experience in applying DSM manual, which is standardized list of symptoms to be checked in every case (in order to be qualified as a certain disorder). It is perfectly possible that two persons diagnosed with the same disorder have not overlapping symptoms, and that one person can have two distinct diagnosis. If someone has more than three episodes of depression, that is considered to be recurrent depression (after every episode the probability of the next one is doubling). This is particularly heard to treat and manage therapy which is ongoing through person's whole life. Apart from obsolete diagnostic, all antidepressants have serious side-effects, the waiting lists are very long (in Nederland they are between 6 and 9 months long) and the therapy can last for years or even decades. It is reported than only 11 - 30% of patients are improving in the first year of therapy (Rush et al., 2008).

Simulated warfare between artificial intelligence participants has revealed that "extraordinary forms" of extreme weaponry evolve when combatants fight each other in one-to-one in duels. Researchers at the University of Auckland in New Zealand pitted AI players against each other in a war game to better understand how animals evolve weapons. They found that combatants with improved weapons had a large advantage when fighting in duels, but that this advantage deteriorated when there were more rivals to fight against. The findings suggest that arms races between animals and in other types of conflict are more likely to be accelerated when there are only two opponents. The study was based on a current evolutionary hypothesis that predicts the evolution of elaborate weaponry in duel-based systems, such as the exaggerated horns wielded by male dung beetles and stag deer when fighting over females.

In October, Amazon had to discontinue an artificial intelligence–powered recruiting tool after it discovered the system was biased against female applicants. In 2016, a ProPublica investigation revealed a recidivism assessment tool that used machine learning was biased against black defendants. More recently, the US Department of Housing and Urban Development sued Facebook because its ad-serving algorithms enabled advertisers to discriminate based on characteristics like gender and race. And Google refrained from renewing its AI contract with the Department of Defense after employees raised ethical concerns. Those are just a few of the many ethical controversies surrounding artificial intelligence algorithms in the past few years.

Translating from languages without productive grammatical gender like English into gender-marked languages is a well-known difficulty for machines. This difficulty is also due to the fact that the training data on which models are built typically reflect the asymmetries of natural languages, gender bias included. Exclusively fed with textual data, machine translation is intrinsically constrained by the fact that the input sentence does not always contain clues about the gender identity of the referred human entities. But what happens with speech translation, where the input is an audio signal? Can audio provide additional information to reduce gender bias? We present the first thorough investigation of gender bias in speech translation, contributing with: i) the release of a benchmark useful for future studies, and ii) the comparison of different technologies (cascade and end-to-end) on two language directions (English-Italian/French).

The number of Earth observation satellites carrying optical sensors with similar characteristics is constantly growing. Despite their similarities and the potential synergies among them, derived satellite products are often developed for each sensor independently. Differences in retrieved radiances lead to significant drops in accuracy, which hampers knowledge and information sharing across sensors. This is particularly harmful for machine learning algorithms, since gathering new ground truth data to train models for each sensor is costly and requires experienced manpower. In this work, we propose a domain adaptation transformation to reduce the statistical differences between images of two satellite sensors in order to boost the performance of transfer learning models. The proposed methodology is based on the Cycle Consistent Generative Adversarial Domain Adaptation (CyCADA) framework that trains the transformation model in an unpaired manner. In particular, Landsat-8 and Proba-V satellites, which present different but compatible spatio-spectral characteristics, are used to illustrate the method. The obtained transformation significantly reduces differences between the image datasets while preserving the spatial and spectral information of adapted images, which is hence useful for any general purpose cross-sensor application. In addition, the training of the proposed adversarial domain adaptation model can be modified to improve the performance in a specific remote sensing application, such as cloud detection, by including a dedicated term in the cost function. Results show that, when the proposed transformation is applied, cloud detection models trained in Landsat-8 data increase cloud detection accuracy in Proba-V.

We approach the problem of learning continuous normalizing flows from a dual perspective motivated by entropy-regularized optimal transport, in which continuous normalizing flows are cast as gradients of scalar potential functions. This formulation allows us to train a dual objective comprised only of the scalar potential functions, and removes the burden of explicitly computing normalizing flows during training. After training, the normalizing flow is easily recovered from the potential functions.