With the great success of Graph Neural Networks (GNNs) towards representation learning on graph-structure data, the robustness of GNNs against adversarial attack inevitably becomes a central problem in graph learning domain. Regardless of the fruitful progress, current works suffer from two main limitations: First, the attack method required to be developed case by case; Second, most of them are restricted to the white-box attack. This paper promotes current frameworks in a more general and flexible sense -- we demand only one single method to attack various kinds of GNNs and this attacker is black box driven. To this end, we begin by investigating the theoretical connections between different kinds of GNNs in a principled way and integrate different GNN models into a unified framework, dubbed as General Spectral Graph Convolution. As such, a generalized adversarial attacker is proposed towards two families of GNNs: Convolution-based model and sampling-based model. More interestingly, our attacker does not require any knowledge of the target classifiers used in GNNs. Extensive experimental results validate the effectiveness of our method on several benchmark datasets. Particularly by using our attack, even small graph perturbations like one-edge flip is able to consistently make a strong attack in performance to different GNN models.

A new and an enriched JPEG algorithm is provided for identifying redundancies in a sequence of irregular noisy data points which also accommodates a reference-free criterion function. Our main contribution is by formulating analytically (instead of approximating) the inverse of the transpose of JPEGwavelet transform without involving matrices which are computationally cumbersome. The algorithm is suitable for the widely-spread situations where the original data distribution is unobservable such as in cases where there is deficient representation of the entire population in the training data (in machine learning) and thus the covariate shift assumption is violated. The proposed estimator corrects for both biases, the one generated by endogenous truncation and the one generated by endogenous covariates. Results from utilizing 2,000,000 different distribution functions verify the applicability and high accuracy of our procedure to cases in which the disturbances are neither jointly nor marginally normally distributed.

Graph clustering is a basic technique in machine learning, and has widespread applications in different domains. While spectral techniques have been successfully applied for clustering undirected graphs, the performance of spectral clustering algorithms for directed graphs (digraphs) is not in general satisfactory: these algorithms usually require symmetrising the matrix representing a digraph, and typical objective functions for undirected graph clustering do not capture cluster-structures in which the information given by the direction of the edges is crucial. To overcome these downsides, we propose a spectral clustering algorithm based on a complex-valued matrix representation of digraphs. We analyse its theoretical performance on a Stochastic Block Model for digraphs in which the cluster-structure is given not only by variations in edge densities, but also by the direction of the edges. The significance of our work is highlighted on a data set pertaining to internal migration in the United States: while previous spectral clustering algorithms for digraphs can only reveal that people are more likely to move between counties that are geographically close, our approach is able to cluster together counties with a similar socio-economical profile even when they are geographically distant, and illustrates how people tend to move from rural to more urbanised areas.

This paper presents an investigation of using a co-attention based neural network for source-dependent essay scoring. We use a co-attention mechanism to help the model learn the importance of each part of the essay more accurately. Also, this paper shows that the co-attention based neural network model provides reliable score prediction of source-dependent responses. We evaluate our model on two source-dependent response corpora. Results show that our model outperforms the baseline on both corpora. We also show that the attention of the model is similar to the expert opinions with examples.

Many of California's local law enforcement agencies have access to facial recognition software for identifying suspects who appear in crime scene footage, documents obtained through public records requests show. Three California counties also have the capability to run facial recognition searches on each others' mug shot databases, and others could join if they choose to opt into a network maintained by a private law enforcement software company. The network is called California Facial Recognition Interconnect, and it's a service offered by DataWorks Plus, a Greenville, South Carolina–based company with law enforcement contracts in Los Angeles, San Bernardino, San Diego, San Francisco, Sacramento, and Santa Barbara. Currently, the three adjacent counties of Los Angeles, Riverside, and San Bernardino are able to run facial recognition against mug shots in each other's databases. That means these police departments have access to about 11.7 million mug shots of people who have previously been arrested, a majority of which come from the Los Angeles system.

Stroke patients or others with neurological injury are turning to the rehabilitation powers of robots with artificial intelligence that help people regain previously lost mobility. BIONIK Laboratories, a global health care company with an office in Watertown, develops robotic "InMotion" systems for the arm, hand and wrist. The FDA-cleared products, which are used in hospitals and rehabilitation facilities, work seamlessly by guiding patients with the help of a physical therapist through various movement activities displayed on a monitor. Once the patient has a hand and arm in the InMotion device, robotic therapy takes over, using artificial intelligence to provide the patient as much assistance as needed to work through a series of movements aimed at regaining the patient's mobility. Dr. Eric Dusseux, CEO of BIONIK, said, "We have demonstrated that by using robotic therapy, you can heal faster and better than any conventional therapy. Dusseux said the autonomy and self-esteem experienced by patients using the robots "is exactly what you need when you're a patient suffering from neurological disease." The system even has therapies styled like video games for younger patients. A typical session with the robot may last 30 minutes to an hour, with thousands of people using the 250 systems that have been implemented in over 20 countries. Dusseux said the artificial intelligence data is processed to help patients and doctors get a good idea of progress, often boosting the spirits of those who are frustrated with their limited mobility. "You can imagine the support for the first time after your stroke.

ELYAKIM ARMY BASE, ISRAEL – Israel, a world leader in hi-tech, is around 30 years away from its ambition of deploying robot forces, and for now will chose between three prototypes of semi-automated armored vehicles to cocoon its troops in battle, defense officials said on Sunday. Israel has long eyed a future robot army as a means of reducing the use of soldiers on its combustible fronts with Gaza, Lebanon and Syria, just as its air force has increasingly relied on pilot-less drones. The country draws most of its military personnel from teenage conscripts. An unveiling of Israel's newly developed operating suites for ground fighting vehicles made clear it plans to keep soldiers at the controls, albeit entirely insulated from the outside: Hatches battened, the cabins will have smart-screens, fed by outside cameras and sensors, instead of windows or ports. "Now the people will be sitting in the tank, it's closed, they are far better protected, and they can advance without worrying about snipers or other things," said Brig.

Deep Neural Networks (DNNs) deliver state-of-the-art performance in many image recognition and understanding applications. However, despite their outstanding performance, these models are black-boxes and it is hard to understand how they make their decisions. Over the past few years, researchers have studied the problem of providing explanations of why DNNs predicted their results. However, existing techniques are either obtrusive, requiring changes in model training, or suffer from low output quality. In this paper, we present a novel method, NeuroMask, for generating an interpretable explanation of classification model results. When applied to image classification models, NeuroMask identifies the image parts that are most important to classifier results by applying a mask that hides/reveals different parts of the image, before feeding it back into the model. The mask values are tuned by minimizing a properly designed cost function that preserves the classification result and encourages producing an interpretable mask. Experiments using state-of-the-art Convolutional Neural Networks for image recognition on different datasets (CIFAR-10 and ImageNet) show that NeuroMask successfully localizes the parts of the input image which are most relevant to the DNN decision. By showing a visual quality comparison between NeuroMask explanations and those of other methods, we find NeuroMask to be both accurate and interpretable.

Corrigibility is a safety property for artificially intelligent agents. A corrigible agent will not resist attempts by authorized parties to alter the goals and constraints that were encoded in the agent when it was first started. This paper shows how to construct a safety layer that adds corrigibility to arbitrarily advanced utility maximizing agents, including possible future agents with Artificial General Intelligence (AGI). The layer counter-acts the emergent incentive of advanced agents to resist such alteration. A detailed model for agents which can reason about preserving their utility function is developed, and used to prove that the corrigibility layer works as intended in a large set of non-hostile universes. The corrigible agents have an emergent incentive to protect key elements of their corrigibility layer. However, hostile universes may contain forces strong enough to break safety features. Some open problems related to graceful degradation when an agent is successfully attacked are identified. The results in this paper were obtained by concurrently developing an AGI agent simulator, an agent model, and proofs. The simulator is available under an open source license. The paper contains simulation results which illustrate the safety related properties of corrigible AGI agents in detail.