Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification. However, only few work has addressed the adversarial robustness of GNNs. In this paper, we first present a novel gradient-based attack method that facilitates the difficulty of tackling discrete graph data. When comparing to current adversarial attacks on GNNs, the results show that by only perturbing a small number of edge perturbations, including addition and deletion, our optimization-based attack can lead to a noticeable decrease in classification performance. Moreover, leveraging our gradient-based attack, we propose the first optimization-based adversarial training for GNNs. Our method yields higher robustness against both different gradient based and greedy attack methods without sacrificing classification accuracy on original graph.

In this paper, the authors aim to combine the latest state of the art models in image recognition with the best publicly available satellite images to create a system for landslide risk mitigation. We focus first on landslide detection and further propose a similar system to be used for prediction. Such models are valuable as they could easily be scaled up to provide data for hazard evaluation, as satellite imagery becomes increasingly available. The goal is to use satellite images and correlated data to enrich the public repository of data and guide disaster relief efforts for locating precise areas where landslides have occurred. Different image augmentation methods are used to increase diversity in the chosen dataset and create more robust classification. The resulting outputs are then fed into variants of 3-D convolutional neural networks. A review of the current literature indicates there is no research using CNNs (Convolutional Neural Networks) and freely available satellite imagery for classifying landslide risk. The model has shown to be ultimately able to achieve a significantly better than baseline accuracy.

We propose a simple change to the current neural network structure for defending against gradient-based adversarial attacks. Instead of using popular activation functions (such as ReLU), we advocate the use of $k$-Winners-Take-All ($k$-WTA) activation, a $C^0$ discontinuous function that purposely invalidates the neural network model's gradient at densely distributed input data points. Our proposal is theoretically rationalized. We show why the discontinuities in $k$-WTA networks can largely prevent gradient-based search of adversarial examples and why they at the same time remain innocuous to the network training. This understanding is also empirically backed. Even without notoriously expensive adversarial training, the robustness performance of our networks is comparable to conventional ReLU networks optimized by adversarial training. Furthermore, after also optimized through adversarial training, our networks outperform the state-of-the-art methods under white-box attacks on various datasets that we experimented with.

Artificial intelligence is quickly becoming a part of daily life. Enterprise implementations of AI-based technologies tripled in 2018, according to Gartner. At the same time, it's reaching ubiquity in consumer-facing applications, helping us write our emails, discover new music, and get on-demand customer support. At every touchpoint, our data is being collected and used to make machines faster and smarter, and that's driving calls for regulation from global citizens, governments, and companies who want to ensure deployments of machine and deep learning algorithms are safe and ethical. While implementing laws to protect consumers from "AI-gone-wild" may seem like a reasonable proposition, it's one that's doomed to fail.

Which Way Next? is a Singularity University webcast series of monthly roundtable discussions on exponential technologies with leaders in industry, science and technology. This is a recording of our live premiere episode with Dr. Sebastian Thrun, PhD, research professor and executive director of the Artificial Intelligence Lab at Stanford University and Google Fellow on Tuesday, Dec. 6, 2011. On this episode, he joined SU Chairman & Co-Founder Dr. Peter Diamandis, MD in a discussion on artificial intelligence and the Google autonomous Car. Earlier this year, Fast Company honored Dr. Thrun with the title of "fifth most creative person in the world." About Singularity University: Singularity University is a benefit corporation headquartered at NASA's research campus in Silicon Valley.

"We will work constructively with other WTO members to undertake necessary WTO reform with a sense of urgency," the statement said. Hiroshige Seko, minister of economy, trade and industry, said that it is significant that specifics concerning WTO reform were included in a G20 ministerial statement for the first time. Improving the organization's system for resolving disputes is one of them. "We agree that action is necessary regarding the functioning of the dispute settlement system consistent with the rules as negotiated by the WTO members," the statement said. Foreign Minister Taro Kono said it was a "big feat" for Japan, which places importance on this issue, that the need to address the system was explicitly mentioned in the statement.

US federal government contract obligations and AI-related investments grew almost 75% to nearly $700 million between fiscal 2016 and 2018 [Federal News Network]. Of those that have adopted an AI-driven marketing solution, 74% reported using AI in an "assistive" fashion, which surfaces insights for marketers to consider during manual decision making. Only 26% of marketers reported using autonomous AI, which can act on its own insights and work collaboratively with marketers (without adding manual work) [Albert and Forrester]. Notable growth came in areas like food and consumer goods (48%), plastics and rubber (37%), life sciences (31%), and electronics (22%) [Robotic Industry Association]. Nearly eight out of 10 enterprise organizations currently engaged in AI and ML report that projects have stalled, and 96% of these companies have run into problems with data quality, data labeling required to train AI, and building model confidence; only half of enterprises have released AI/ML projects into production; 78% of their AI/ML projects stall at some stage before deployment; 81% admit the process of training AI with data is more difficult than they expected; 76% combat this challenge by attempting to label and annotate training data on their own; 63% go so far as to try to build their own labeling and annotation automation technology; 71% report that they ultimately outsource training data and other ML project activities [Alegion and Dimensional Research].

American universities and corporations are in danger of becoming unwilling partners in dual civil-military use of artificial intelligence (AI) technology by the Chinese government, a Congressional Commission hearing was told on Friday. For now, the United States is well ahead of China in the development of AI - essentially, technology that enables machines to learn like humans and apply what they learn. But to maintain the edge, it must do more to support AI research, and it should also remain open to global talent, experts told the US-China Economic and Security and Review Commission (USCC). "Human talent may be the most valuable input into a nation's AI system," Mr Jeffrey Ding, a researcher at the Centre for the Governance of AI at Oxford University, told the commission. And the US has by far the most talent in that area.

Graph Neural Networks (GNNs) have boosted the performance of many graph related tasks such as node classification and graph classification. Recent researches show that graph neural networks are vulnerable to adversarial attacks, which deliberately add carefully created unnoticeable perturbation to the graph structure. The perturbation is usually created by adding/deleting a few edges, which might be noticeable even when the number of edges modified is small. In this paper, we propose a graph rewiring operation which affects the graph in a less noticeable way compared to adding/deleting edges. We then use reinforcement learning to learn the attack strategy based on the proposed rewiring operation. Experiments on real world graphs demonstrate the effectiveness of the proposed framework. To understand the proposed framework, we further analyze how its generated perturbation to the graph structure affects the output of the target model.

CNNs, RNNs, GCNs, and CapsNets have shown significant insights in representation learning and are widely used in various text mining tasks such as large-scale multi-label text classification. However, most existing deep models for multi-label text classification consider either the non-consecutive and long-distance semantics or the sequential semantics, but how to consider them both coherently is less studied. In addition, most existing methods treat output labels as independent methods, but ignore the hierarchical relations among them, leading to useful semantic information loss. In this paper, we propose a novel hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework for large-scale multi-label text classification. Specifically, we first propose to model each document as a word order preserved graph-of-words and normalize it as a corresponding words-matrix representation which preserves both the non-consecutive, long-distance and local sequential semantics. Then the words-matrix is input to the proposed attentional graph capsule recurrent CNNs for more effectively learning the semantic features. To leverage the hierarchical relations among the class labels, we propose a hierarchical taxonomy embedding method to learn their representations, and define a novel weighted margin loss by incorporating the label representation similarity. Extensive evaluations on three datasets show that our model significantly improves the performance of large-scale multi-label text classification by comparing with state-of-the-art approaches.