Russia has downed 53 Ukrainian drones, the majority of which targeted the southern Rostov region, the Ministry of Defence said, as the Kremlin warned that Russia and NATO are now in "direct confrontation" over Ukraine. The ministry said that "terrorist attacks with aerial drones" overnight and on Friday morning were foiled, adding that 44 of them were downed or intercepted in Rostov, where Russia's Ukraine campaign headquarters is located. Vasily Golubev, the governor of Rostov, confirmed early on Friday that air defence units had destroyed more than 40 airborne targets, though an electricity substation was damaged. Writing on the Telegram messaging app, he said the drone attacks had focused on the Morozovsk district, northeast of Rostov, which lies on Ukraine's eastern border. Golubev said work was under way to restore power supplies in the affected areas.

A Ukrainian unmanned aerial vehicle (UAV) that hit Russia's Tatarstan region this week was likely a modified Ukrainian-made Aeroprakt A-22 light aircraft, several experts said, offering insight into one of Kyiv's deepest drone strikes to date. Russia said the attack hit an industrial site's dorms and hurt 13 people. A Kyiv intelligence source said it struck a site used to produce Russian long-range drones that have been used in the thousands to pound Ukraine during the 25-month war. Russian media reported that two drones struck the dormitory at Russia's Alabuga Special Economic Zone, which is located more than 1,200 kilometers from Ukraine's northeastern city of Kharkiv near the Russian border. It is unclear what the second drone was.

China will attempt to disrupt elections in the US, South Korea and India this year with artificial intelligence-generated content after making a dry run with the presidential poll in Taiwan, Microsoft has warned. The US tech firm said it expected Chinese state-backed cyber groups to target high-profile elections in 2024, with North Korea also involved, according to a report by the company's threat intelligence team published on Friday. "As populations in India, South Korea and the United States head to the polls, we are likely to see Chinese cyber and influence actors, and to some extent North Korean cyber actors, work toward targeting these elections," the report reads. Microsoft said that "at a minimum" China will create and distribute through social media AI-generated content that "benefits their positions in these high-profile elections". The company added that the impact of AI-made content was minor but warned that could change.

The field of visually rich document understanding (VRDU) aims to solve a multitude of well-researched NLP tasks in a multi-modal domain. Several datasets exist for research on specific tasks of VRDU such as document classification (DC), key entity extraction (KEE), entity linking, visual question answering (VQA), inter alia. These datasets cover documents like invoices and receipts with sparse annotations such that they support one or two co-related tasks (e.g., entity extraction and entity linking). Unfortunately, only focusing on a single specific of documents or task is not representative of how documents often need to be processed in the wild - where variety in style and requirements is expected. In this paper, we introduce BuDDIE (Business Document Dataset for Information Extraction), the first multi-task dataset of 1,665 real-world business documents that contains rich and dense annotations for DC, KEE, and VQA. Our dataset consists of publicly available business entity documents from US state government websites. The documents are structured and vary in their style and layout across states and types (e.g., forms, certificates, reports, etc.). We provide data variety and quality metrics for BuDDIE as well as a series of baselines for each task. Our baselines cover traditional textual, multi-modal, and large language model approaches to VRDU.

The growing cybersecurity threats make it essential to use high-quality data to train Machine Learning (ML) models for network traffic analysis, without noisy or missing data. By selecting the most relevant features for cyber-attack detection, it is possible to improve both the robustness and computational efficiency of the models used in a cybersecurity system. This work presents a feature selection and consensus process that combines multiple methods and applies them to several network datasets. Two different feature sets were selected and were used to train multiple ML models with regular and adversarial training. Finally, an adversarial evasion robustness benchmark was performed to analyze the reliability of the different feature sets and their impact on the susceptibility of the models to adversarial examples. By using an improved dataset with more data diversity, selecting the best time-related features and a more specific feature set, and performing adversarial training, the ML models were able to achieve a better adversarially robust generalization. The robustness of the models was significantly improved without their generalization to regular traffic flows being affected, without increases of false alarms, and without requiring too many computational resources, which enables a reliable detection of suspicious activity and perturbed traffic flows in enterprise computer networks.

Climate change exacerbates extreme weather events like heavy rainfall and flooding. As these events cause severe losses of property and lives, accurate high-resolution simulation of precipitation is imperative. However, existing Earth System Models (ESMs) struggle with resolving small-scale dynamics and suffer from biases, especially for extreme events. Traditional statistical bias correction and downscaling methods fall short in improving spatial structure, while recent deep learning methods lack controllability over the output and suffer from unstable training. Here, we propose a novel machine learning framework for simultaneous bias correction and downscaling. We train a generative diffusion model in a supervised way purely on observational data. We map observational and ESM data to a shared embedding space, where both are unbiased towards each other and train a conditional diffusion model to reverse the mapping. Our method can be used to correct any ESM field, as the training is independent of the ESM. Our approach ensures statistical fidelity, preserves large-scale spatial patterns and outperforms existing methods especially regarding extreme events and small-scale spatial features that are crucial for impact assessments.

This article investigates how AI-generated content can disrupt central revenue streams of the creative industries, in particular the collection of dividends from intellectual property (IP) rights. It reviews the IP and copyright questions related to the input and output of generative AI systems. A systematic method is proposed to assess whether AI-generated outputs, especially images, infringe previous copyrights, using a similarity metric (CLIP) between images against historical copyright rulings. An examination (economic and technical feasibility) of previously proposed compensation frameworks reveals their financial implications for creatives and IP holders. Lastly, we propose a novel IP framework for compensation of artists and IP holders based on their published "licensed AIs" as a new medium and asset from which to collect AI royalties.

To reach high performance with deep learning, hyperparameter optimization (HPO) is essential. This process is usually time-consuming due to costly evaluations of neural networks. Early discarding techniques limit the resources granted to unpromising candidates by observing the empirical learning curves and canceling neural network training as soon as the lack of competitiveness of a candidate becomes evident. Despite two decades of research, little is understood about the trade-off between the aggressiveness of discarding and the loss of predictive performance. Our paper studies this trade-off for several commonly used discarding techniques such as successive halving and learning curve extrapolation. Our surprising finding is that these commonly used techniques offer minimal to no added value compared to the simple strategy of discarding after a constant number of epochs of training. The chosen number of epochs depends mostly on the available compute budget. We call this approach i-Epoch (i being the constant number of epochs with which neural networks are trained) and suggest to assess the quality of early discarding techniques by comparing how their Pareto-Front (in consumed training epochs and predictive performance) complement the Pareto-Front of i-Epoch.

The third ML4H symposium was held in person on December 10, 2023, in New Orleans, Louisiana, USA. The symposium included research roundtable sessions to foster discussions between participants and senior researchers on timely and relevant topics for the \ac{ML4H} community. Encouraged by the successful virtual roundtables in the previous year, we organized eleven in-person roundtables and four virtual roundtables at ML4H 2022. The organization of the research roundtables at the conference involved 17 Senior Chairs and 19 Junior Chairs across 11 tables. Each roundtable session included invited senior chairs (with substantial experience in the field), junior chairs (responsible for facilitating the discussion), and attendees from diverse backgrounds with interest in the session's topic. Herein we detail the organization process and compile takeaways from these roundtable discussions, including recent advances, applications, and open challenges for each topic. We conclude with a summary and lessons learned across all roundtables. This document serves as a comprehensive review paper, summarizing the recent advancements in machine learning for healthcare as contributed by foremost researchers in the field.

Sentiment analysis plays a pivotal role in understanding public opinion, particularly in the political domain where the portrayal of entities in news articles influences public perception. In this paper, we investigate the effectiveness of Large Language Models (LLMs) in predicting entity-specific sentiment from political news articles. Leveraging zero-shot and few-shot strategies, we explore the capability of LLMs to discern sentiment towards political entities in news content. Employing a chain-of-thought (COT) approach augmented with rationale in few-shot in-context learning, we assess whether this method enhances sentiment prediction accuracy. Our evaluation on sentiment-labeled datasets demonstrates that LLMs, outperform fine-tuned BERT models in capturing entity-specific sentiment. We find that learning in-context significantly improves model performance, while the self-consistency mechanism enhances consistency in sentiment prediction. Despite the promising results, we observe inconsistencies in the effectiveness of the COT prompting method. Overall, our findings underscore the potential of LLMs in entity-centric sentiment analysis within the political news domain and highlight the importance of suitable prompting strategies and model architectures.