Recent named entity recognition (NER) models often rely on human-annotated datasets, requiring the significant engagement of professional knowledge on the target domain and entities. This research introduces an ask-to-generate approach that automatically generates NER datasets by asking questions in simple natural language to an open-domain question answering system (e.g., "Which disease?"). Despite using fewer in-domain resources, our models, solely trained on the generated datasets, largely outperform strong low-resource models by an average F1 score of 19.4 for six popular NER benchmarks. Furthermore, our models provide competitive performance with rich-resource models that additionally leverage in-domain dictionaries provided by domain experts. In few-shot NER, we outperform the previous best model by an F1 score of 5.2 on three benchmarks and achieve new state-of-the-art performance.

Recent studies on adversarial images have shown that they tend to leave the underlying low-dimensional data manifold, making them significantly more challenging for current models to make correct predictions. This so-called off-manifold conjecture has inspired a novel line of defenses against adversarial attacks on images. In this study, we find a similar phenomenon occurs in the contextualized embedding space induced by pretrained language models, in which adversarial texts tend to have their embeddings diverge from the manifold of natural ones. Based on this finding, we propose Textual Manifold-based Defense (TMD), a defense mechanism that projects text embeddings onto an approximated embedding manifold before classification. It reduces the complexity of potential adversarial examples, which ultimately enhances the robustness of the protected model. Through extensive experiments, our method consistently and significantly outperforms previous defenses under various attack settings without trading off clean accuracy. To the best of our knowledge, this is the first NLP defense that leverages the manifold structure against adversarial attacks. Our code is available at \url{https://github.com/dangne/tmd}.

Federated learning (FL) is a promising way to allow multiple data owners (clients) to collaboratively train machine learning models without compromising data privacy. Yet, existing FL solutions usually rely on a centralized aggregator for model weight aggregation, while assuming clients are honest. Even if data privacy can still be preserved, the problem of single-point failure and data poisoning attack from malicious clients remains unresolved. To tackle this challenge, we propose to use distributed ledger technology (DLT) to achieve FLock, a secure and reliable decentralized Federated Learning system built on blockchain. To guarantee model quality, we design a novel peer-to-peer (P2P) review and reward/slash mechanism to detect and deter malicious clients, powered by on-chain smart contracts. The reward/slash mechanism, in addition, serves as incentives for participants to honestly upload and review model parameters in the FLock system. FLock thus improves the performance and the robustness of FL systems in a fully P2P manner.

Strong gravitational lensing has emerged as a promising approach for probing dark matter models on sub-galactic scales. Recent work has proposed the subhalo effective density slope as a more reliable observable than the commonly used subhalo mass function. The subhalo effective density slope is a measurement independent of assumptions about the underlying density profile and can be inferred for individual subhalos through traditional sampling methods. To go beyond individual subhalo measurements, we leverage recent advances in machine learning and introduce a neural likelihood-ratio estimator to infer an effective density slope for populations of subhalos. We demonstrate that our method is capable of harnessing the statistical power of multiple subhalos (within and across multiple images) to distinguish between characteristics of different subhalo populations. The computational efficiency warranted by the neural likelihood-ratio estimator over traditional sampling enables statistical studies of dark matter perturbers and is particularly useful as we expect an influx of strong lensing systems from upcoming surveys.

We tackle the problem of tracking the human lower body as an initial step toward an automatic motion assessment system for clinical mobility evaluation, using a multimodal system that combines Inertial Measurement Unit (IMU) data, RGB images, and point cloud depth measurements. This system applies the factor graph representation to an optimization problem that provides 3-D skeleton joint estimations. In this paper, we focus on improving the temporal consistency of the estimated human trajectories to greatly extend the range of operability of the depth sensor. More specifically, we introduce a new factor graph factor based on Koopman theory that embeds the nonlinear dynamics of several lower-limb movement activities. This factor performs a two-step process: first, a custom activity recognition module based on spatial temporal graph convolutional networks recognizes the walking activity; then, a Koopman pose prediction of the subsequent skeleton is used as an a priori estimation to drive the optimization problem toward more consistent results. We tested the performance of this module on datasets composed of multiple clinical lowerlimb mobility tests, and we show that our approach reduces outliers on the skeleton form by almost 1 m, while preserving natural walking trajectories at depths up to more than 10 m.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Chief diplomats from the world's leading democracies rallied together in a joint statement condemning global adversaries like Iran and North Korea and called on Russia and China to remember their security commitments to the United Nations. After two days of meetings, officials from the Group of 7 (G7) released a lengthy statement Friday in an address to its top geopolitical challengers, warning them to adhere to international laws. United States Secretary of States Antony Blinken and Foreign Minister Yoshimasa Hayashi of Japan, right, meet for bilateral talks at the G7 Foreign Ministers' Meeting in Muenster, Germany, Friday, Nov. 4, 2022.

The United States will fund the refurbishment of T-72 tanks and HAWK surface-to-air missiles as part of a roughly $400 million security assistance package for Ukraine, the Pentagon announced Friday. Air defense and armor capabilities are both high on the list of assistance desired by Ukraine, but the T-72s fall short of more modern tanks such as the German Leopard or US Abrams that have been sought by Kyiv. The "tanks are coming from the Czech Republic defense industry, and the United States is paying for 45 of those to be refurbished, and the government of the Netherlands is matching our commitment" for a total of 90 T-72s, Deputy Pentagon Press Secretary Sabrina Singh told journalists. The T-72s -- a Soviet-era tank -- will be equipped with "advanced optics, communications and armor packages," with some ready by the end of December and others to be delivered in 2023, she said. Asked why more modern tanks were not being provided, Singh cited factors including ease of use and cost. "These are tanks that the Ukrainians know how to use on the battlefield," she said, adding that "introducing a new main battle tank is extremely costly, is time sensitive, and it would be a huge undertaking for the Ukrainian forces."

The United Kingdom's National Cyber Security Centre (NCSC), the government agency that leads the country's cyber security mission, is now scanning all Internet-exposed devices hosted in the UK for vulnerabilities. The goal is to assess UK's vulnerability to cyber-attacks and to help the owners of Internet-connected systems understand their security posture. "These activities cover any internet-accessible system that is hosted within the UK and vulnerabilities that are common or particularly important due to their high impact," the agency said. "The NCSC uses the data we have collected to create an overview of the UK's exposure to vulnerabilities following their disclosure, and track their remediation over time." NCSC's scans are performed using tools hosted in a dedicated cloud-hosted environment from scanner.scanning.service.ncsc.gov.uk and two IP addresses (18.171.7.246 and 35.177.10.231).

Innovative companies in virtually every industry--from healthcare and investing to transportation and manufacturing--are rapidly adopting artificial intelligence (AI) and machine learning to accomplish sophisticated tasks with increasing accuracy and precision. As these revolutionary technologies evolve and improve, they are becoming an important element in enhancing an ever-growing list of applications, including customer service, logistics, and safety. Wilson Sonsini's artificial intelligence and machine learning team has worked with hundreds of companies in the AI space. Clients rely on us to help them protect and commercialize their AI technologies, in-license AI technologies from start-ups and academic institutions, litigate AI-related IP disputes, and navigate the complex legal and regulatory landscape governing this dynamic field. Because many of our team's attorneys and staff professionals have relevant technical backgrounds, we understand the unique nuances and challenges of this field.

The Bank of England has published its report "Machine Learning in UK Financial Services". The report sets out its findings, following a survey of around a hundred regulated firms in the UK. It highlights the growing use of machine learning, especially in insurance, and the challenges of explainability, legacy systems, the skills gap and regulatory uncertainty. The number of UK financial services firms using or developing machine learning (ML) applications is increasing, and this trend is set to continue across a greater range of business areas within financial services. The largest expected increase in use, in absolute terms, is in the insurance sector, followed by banking.