Despite achieving strong performance in the semi-supervised node classification task, graph neural networks (GNNs) are vulnerable to adversarial attacks, similar to other deep learning models. Existing research works either focus on developing robust GNN models or attack detection methods against attacks on graphs. However, little research attention is paid to the potential and practice of immunization to adversarial attacks on graphs. In this paper, we formulate the problem of graph adversarial immunization as a bilevel optimization problem, i.e., vaccinating an affordable fraction of node pairs, connected or unconnected, to improve the certifiable robustness of the graph against any admissible adversarial attack. We further propose an efficient algorithm, called AdvImmune, which optimizes meta-gradient in a discrete way to circumvent the computationally expensive combinatorial optimization when solving the adversarial immunization problem. Experiments are conducted on two citation networks and one social network. Experimental results demonstrate that the proposed AdvImmune immunization method remarkably improves the fraction of robust nodes by 12%, 42%, 65%, with an affordable immune budget of only 5% edges.

Face recognition systems are present in many modern solutions and thousands of applications in our daily lives. However, current solutions are not easily scalable, especially when it comes to the addition of new targeted people. We propose a cluster-matching-based approach for face recognition in video. In our approach, we use unsupervised learning to cluster the faces present in both the dataset and targeted videos selected for face recognition. Moreover, we design a cluster matching heuristic to associate clusters in both sets that is also capable of identifying when a face belongs to a non-registered person. Our method has achieved a recall of 99.435% and a precision of 99.131% in the task of video face recognition. Besides performing face recognition, it can also be used to determine the video segments where each person is present.

Since modernity, ethic has been progressively fragmented into specific communities of practice. The digital revolution enabled by AI and Data is bringing ethical wicked problems in the crossroads of technology and behavior. However, the need of a comprehensive and constructive ethical framework is emerging as digital platforms connect us globally. The unequal structure of the global system makes that dynamic changes and systemic problems impact more on those that are most vulnerable. Ethical frameworks based only on the individual-level are not longer sufficient. A new ethical vision must comprise the understanding of the scales and complex interconnections of social systems. Many of these systems are internally fragile and very sensitive to external factors and threats, which turns into unethical situations that require systemic solutions. The high scale nature of digital technology that expands globally has also an impact at the individual level having the risk to make humans beings more homogeneous, predictable and ultimately controllable. To preserve the core of humanity ethic must take a stand to preserve and keep promoting individual rights and uniqueness and cultural heterogeneity tackling the negative trends and impact of digitalization. Only combining human-centered and collectiveness-oriented digital development it will be possible to construct new social models and human-machine interactions that are ethical. This vision requires science to enhance ethical frameworks and principles with the actionable insights of relationships and properties of the social systems that may not be evident and need to be quantified and understood to be solved. Artificial Intelligence is both a risk and and opportunity for an ethical development, thus we need a conceptual construct that drives towards a better digitalizated world.

Fact-checking is the task of verifying the veracity of claims by assessing their assertions against credible evidence. The vast majority of fact-checking studies focus exclusively on political claims. Very little research explores fact-checking for other topics, specifically subject matters for which expertise is required. We present the first study of explainable fact-checking for claims which require specific expertise. For our case study we choose the setting of public health. To support this case study we construct a new dataset PUBHEALTH of 11.8K claims accompanied by journalist crafted, gold standard explanations (i.e., judgments) to support the fact-check labels for claims. We explore two tasks: veracity prediction and explanation generation. We also define and evaluate, with humans and computationally, three coherence properties of explanation quality. Our results indicate that, by training on in-domain data, gains can be made in explainable, automated fact-checking for claims which require specific expertise.

Central to the design of many robot systems and their controllers is solving a constrained blackbox optimization problem. This paper presents CNMA, a new method of solving this problem that is conservative in the number of potentially expensive blackbox function evaluations; allows specifying complex, even recursive constraints directly rather than as hard-to-design penalty or barrier functions; and is resilient to the non-termination of function evaluations. CNMA leverages the ability of neural networks to approximate any continuous function, their transformation into equivalent mixed integer linear programs (MILPs) and their optimization subject to constraints with industrial strength MILP solvers. A new learning-from-failure step guides the learning to be relevant to solving the constrained optimization problem. Thus, the amount of learning is orders of magnitude smaller than that needed to learn functions over their entire domains. CNMA is illustrated with the design of several robotic systems: wave-energy propelled boat, lunar lander, hexapod, cartpole, acrobot and parallel parking. These range from 6 real-valued dimensions to 36. We show that CNMA surpasses the Nelder-Mead, Gaussian and Random Search optimization methods against the metric of number of function evaluations.

Deliberate manipulation of digital images can be innocuous (e.g., to improve the quality and appearance of an image) or carried with malicious intent (e.g., to alter the semantic content of the image, or to establish an alibi). The diffusion of fake images has implications on judicial systems, global economy, financial health, and even homeland and national security. Not surprisingly, there have been interest from the digital forensics, and more specifically image forensics, community in recent years to detect deliberate manipulation of digital images. There have also been interest from the commercial market, as suggested in a recent study [1]. Image forensics, an emerging forensic discipline, seeks to determine the history of an image (e.g., its origin), the processing it underwent, etc, in order to determine the authenticity of the images [2].

Cross-modal retrieval relies on accurate models to retrieve relevant results for queries across modalities such as image, text, and video. In this paper, we build upon previous work by tackling the difficulty of evaluating models both quantitatively and qualitatively quickly. We present DIME (Dataset, Index, Model, Embedding), a modality-agnostic tool that handles multimodal datasets, trained models, and data preprocessors to support straightforward model comparison with a web browser graphical user interface. DIME inherently supports building modality-agnostic queryable indexes and extraction of relevant feature embeddings, and thus effectively doubles as an efficient cross-modal tool to explore and search through datasets.

Due to the advancements in cellular technologies and the dense deployment of cellular infrastructure, integrating unmanned aerial vehicles (UAVs) into the fifth-generation (5G) and beyond cellular networks is a promising solution to achieve safe UAV operation as well as enabling diversified applications with mission-specific payload data delivery. In particular, 5G networks need to support three typical usage scenarios, namely, enhanced mobile broadband (eMBB), ultra-reliable low-latency communications (URLLC), and massive machine-type communications (mMTC). On the one hand, UAVs can be leveraged as cost-effective aerial platforms to provide ground users with enhanced communication services by exploiting their high cruising altitude and controllable maneuverability in three-dimensional (3D) space. On the other hand, providing such communication services simultaneously for both UAV and ground users poses new challenges due to the need for ubiquitous 3D signal coverage as well as the strong air-ground network interference. Besides the requirement of high-performance wireless communications, the ability to support effective and efficient sensing as well as network intelligence is also essential for 5G-and-beyond 3D heterogeneous wireless networks with coexisting aerial and ground users. In this paper, we provide a comprehensive overview of the latest research efforts on integrating UAVs into cellular networks, with an emphasis on how to exploit advanced techniques (e.g., intelligent reflecting surface, short packet transmission, energy harvesting, joint communication and radar sensing, and edge intelligence) to meet the diversified service requirements of next-generation wireless systems. Moreover, we highlight important directions for further investigation in future work.

Multi-hop Question Generation (QG) aims to generate answer-related questions by aggregating and reasoning over multiple scattered evidence from different paragraphs. It is a more challenging yet under-explored task compared to conventional single-hop QG, where the questions are generated from the sentence containing the answer or nearby sentences in the same paragraph without complex reasoning. To address the additional challenges in multi-hop QG, we propose Multi-Hop Encoding Fusion Network for Question Generation (MulQG), which does context encoding in multiple hops with Graph Convolutional Network and encoding fusion via an Encoder Reasoning Gate. To the best of our knowledge, we are the first to tackle the challenge of multi-hop reasoning over paragraphs without any sentence-level information. Empirical results on HotpotQA dataset demonstrate the effectiveness of our method, in comparison with baselines on automatic evaluation metrics. Moreover, from the human evaluation, our proposed model is able to generate fluent questions with high completeness and outperforms the strongest baseline by 20.8% in the multi-hop evaluation. The code is publicly available at https://github.com/HLTCHKUST/MulQG}{https://github.com/HLTCHKUST/MulQG .

The Trump administration has released a sweeping strategy outlining steps the executive branch can take to promote and protect the country's competitive advantage on emerging technologies. The White House issued its National Strategy for Critical and Emerging Technologies on Thursday, setting out policy goals for fields that include artificial intelligence, quantum information science, and military and space technologies. The strategy doesn't set specific measures like some of President Donald Trump's executive orders focused on AI and quantum science, but senior administration officials told reporters the strategy signals a new level of coordination among agencies. Priority actions in the strategy include increasing the priority of federal R&D in annual appropriations, accelerating the adoption of emerging technology within agencies and recruiting a workforce with in-demand science and technology skills. Insight by Micro Focus Government Solutions: Learn how NGA is working with artificial intelligence, the adoption of zero trust and how the agency keeps its employees safe from cyber threats in this free webinar.