There is a recent large and growing interest in generative adversarial networks (GANs), which offer powerful features for generative modeling, density estimation, and energy function learning. GANs are difficult to train and evaluate but are capable of creating amazingly realistic, though synthetic, image data. Ideas stemming from GANs such as adversarial losses are creating research opportunities for other challenges such as domain adaptation. In this paper, we look at the field of GANs with emphasis on these areas of emerging research. To provide background for adversarial techniques, we survey the field of GANs, looking at the original formulation, training variants, evaluation methods, and extensions. Then we survey recent work on transfer learning, focusing on comparing different adversarial domain adaptation methods. Finally, we take a look forward to identify open research directions for GANs and domain adaptation, including some promising applications such as sensor-based human behavior modeling.

Given labeled points in a high-dimensional vector space, we seek a low-dimensional subspace such that projecting onto this subspace maintains some prescribed distance between points of differing labels. Intended applications include compressive classification. Taking inspiration from large margin nearest neighbor classification, this paper introduces a semidefinite relaxation of this problem. Unlike its predecessors, this relaxation is amenable to theoretical analysis, allowing us to provably recover a planted projection operator from the data.

Intrusion detection systems (IDSs) generate valuable knowledge about network security, but an abundance of false alarms and a lack of methods to capture the interdependence among alerts hampers their utility for network defense. Here, we explore a graph-based approach for fusing alerts generated by multiple IDSs (e.g., Snort, OSSEC, and Bro). Our approach generates a weighted graph of alert fields (not network topology) that makes explicit the connections between multiple alerts, IDS systems, and other cyber artifacts. We use this multi-modal graph to identify anomalous changes in the alert patterns of a network. To detect the anomalies, we apply the role-dynamics approach, which has successfully identified anomalies in social media, email, and IP communication graphs. In the cyber domain, each node (alert field) in the fused IDS alert graph is assigned a probability distribution across a small set of roles based on that node's features. A cyber attack should trigger IDS alerts and cause changes in the node features, but rather than track every feature for every alert-field node individually, roles provide a succinct, integrated summary of those feature changes. We measure changes in each node's probabilistic role assignment over time, and identify anomalies as deviations from expected roles. We test our approach using simulations including three weeks of normal background traffic, as well as cyber attacks that occur near the end of the simulations. This paper presents a novel approach to multi-modal data fusion and a novel application of role dynamics within the cyber-security domain. Our results show a drastic decrease in the false-positive rate when considering our anomaly indicator instead of the IDS alerts themselves, thereby reducing alarm fatigue and providing a promising avenue for threat intelligence in network defense.

Adversarial attacks against neural networks in a regression setting are a critical yet understudied problem. In this work, we advance the state of the art by investigating adversarial attacks against regression networks and by formulating a more effective defense against these attacks. In particular, we take the perspective that adversarial attacks are likely caused by numerical instability in learned functions. We introduce a stability inducing, regularization based defense against adversarial attacks in the regression setting. Our new and easy to implement defense is shown to outperform prior approaches and to improve the numerical stability of learned functions.

Adversarial examples are considered a serious issue for safety critical applications of AI, such as finance, autonomous vehicle control and medicinal applications. Though significant work has resulted in increased robustness of systems to these attacks, systems are still vulnerable to well-crafted attacks. To address this problem, several adversarial attack detection methods have been proposed. However, a system can still be vulnerable to adversarial samples that are designed to specifically evade these detection methods. One recent detection scheme that has shown good performance is based on uncertainty estimates derived from Monte-Carlo dropout ensembles. Prior Networks, a new method of estimating predictive uncertainty, has been shown to outperform Monte-Carlo dropout on a range of tasks. One of the advantages of this approach is that the behaviour of a Prior Network can be explicitly tuned to, for example, predict high uncertainty in regions where there are no training data samples. In this work, Prior Networks are applied to adversarial attack detection using measures of uncertainty in a similar fashion to Monte-Carlo Dropout. Detection based on measures of uncertainty derived from DNNs and Monte-Carlo dropout ensembles are used as a baseline. Prior Networks are shown to significantly out-perform these baseline approaches over a range of adversarial attacks in both detection of whitebox and blackbox configurations. Even when the adversarial attacks are constructed with full knowledge of the detection mechanism, it is shown to be highly challenging to successfully generate an adversarial sample.

If your professional interests take you to the crossroads of financial services, regulation, compliance, and digital - especially data analytics and machine learning - which altogether is known as regtech, you are in the right place. You are part of statistically small and very geek-oriented professional community, but you know this, and though you might choose not to admit this to strangers at this year's festive parties for fear of causing great pain by boredom, you are in good company with this Contributor and my interviewee. I first met Jo Ann Barefoot when I was chairing the U.K. Financial Conduct Authority (FCA) Industry Sandbox Consultation, where she provided excellent guidance and insights. Jo Ann is one of the most dedicated and busiest advocates of the regtech space on the planet and is truly outstanding in both her knowledge and passion in this area. She dedicates her time to a number of global bodies and initiatives related to regtech: she is a Senior Fellow Emerita at the Harvard Kennedy School Center for Business & Government, a Senior Advisor to the Omidyar network, sits on the fintech advisory committee for FINRA, is an Executive Board Member of the International RegTech Association (IRTA), is a member of the Milken Institute U.S. FinTech Advisory Committee, and chairs the boards of the Center for Financial Services Innovation and FinRegLab.

Rudy Giuliani, one of Donald Trump's closest aides, has posted a bizarre and angry tweet after falling victim to a prank. Mr Giuliani, who served as the president's lawyer and also his cybersecurity advisor, suggested that Twitter had pulled a trick on him because they dislike Mr Trump. But nothing of the sort happened, and Mr Giuliani actually appears to have tricked himself. Now he appears to be spreading conspiracy theories about Twitter in an attempt to deflect from that mistake. Uber has halted testing of driverless vehicles after a woman was killed by one of their cars in Tempe, Arizona.

Every year, Accenture's Technology Vision pinpoints the key technology trends that will reshape and reinvent organisations of all kinds over the next few years. This year's top-line theme is "The Intelligent Enterprise Unleashed". It's a concept that's hugely relevant not only to all businesses, but also – in my view – to armed forces the world over. Why? Because, in the defence context, becoming a more intelligent military organisation is clearly a critical goal. And – as with any other type of organisation – it's a goal that armed forces can only achieve by unlocking the data that's currently held within silos and freeing it up to flow to the right place at the right time for the right use.

German astronaut Alexander Gerst talked with the artificially intelligent crew-assistant CIMON during a 90-minute experiment on Nov. 15 aboard the International Space Station (ISS). According to a statement from the manufacturer, Airbus, Gerst, the commander of the current space station crew, woke up CIMON (the Crew Interactive Mobile CompanioN) with the words "Wake up, CIMON." In response, CIMON said, "What can I do for you?" [This Flying Space Droid Wants to Make Friends with Astronauts] During the experiment, CIMON successfully found and recognized Gerst's face, took photos and video, positioned itself autonomously within the Columbus module using its ultrasonic sensors, and issued instructions for Gerst to perform a student-designed experiment with crystals. Weighing about 5 kilograms (11 lbs. on Earth), the 3D-printed robot designed jointly by the German space agency DLR, Airbus and IBM works similarly to Apple's virtual assistant Siri or Amazon's Alexa. "If CIMON is asked a question or addressed, the Watson AI firstly converts this audio signal into text, which is understood, or interpreted, by the AI," explained IBM project lead Matthias Biniok in the statement.

Myra and Gia were godsend. If tourists start booking Shimla holidays to enjoy the snow and traffic outstrips the number of rooms, the duo sends alerts to hotel chains in the region to increase online inventory. They forecast demand, answer customer queries and can even update on flight delays. The duo has been at the travel portal's headquarters in Cyber City, Gurgaon, for just a year but has already moved on to solving more difficult tasks such as managing loyalty programmes. Whether cancellations or refunds from 12,000-15,000 customer interactions every day, about 60% are resolved by the duo and some of their other techsavvy mates.