In recent decades, numerical weather predictions (NWPs) and their post-processing have played a central role in issuing weather forecasts, warnings, and advisories [WMO, 2013, Vannitsem el al., 2021]. NWP centers around the world have developed and are operating a variety of NWP models for accurate weather predictions. For example, the European Centre for Medium-Range Weather Forecasts (ECMWF) operates the Integrated Forecasting System (IFS) and its ensemble prediction system [ECMWF, 2024]; the UK Met Office operates the Unified Model and the Met Office Global and Regional Ensemble Prediction System [Brown et al., 2012, Hagelin et al., 2017, Inverarity et al., 2023]. The National Centers for Environmental Prediction (NCEP) at the National Oceanic and Atmospheric Administration (NOAA) operates the Global Forecast System [NCEP, 2016], the High-Resolution Rapid Refresh [Dowell et al., 2022], and the Hurricane Weather Research and Forecasting model [Gopalakrishnan et al., 2011]. The Japan Meteorological Agency (JMA) operates three deterministic NWP models and two ensemble prediction systems for short-range to weekly forecasts: the Global Spectrum Model (GSM), the Meso-Scale Model (MSM), the Local Forecast Model, the Global Ensemble Prediction System, and the Mesoscale Ensemble Prediction System [JMA, 2024]. These models cover different areas with varying resolutions and processes. In addition to traditional physics-based NWP models, recent advancements in artificial intelligence (AI) have introduced new methods for producing weather predictions.

The remarkable advances in deep learning have led to the emergence of many off-the-shelf classifiers, e.g., large pre-trained models. However, since they are typically trained on clean data, they remain vulnerable to adversarial attacks. Despite this vulnerability, their superior performance and transferability make off-the-shelf classifiers still valuable in practice, demanding further work to provide adversarial robustness for them in a post-hoc manner. A recently proposed method, denoised smoothing, leverages a denoiser model in front of the classifier to obtain provable robustness without additional training. However, the denoiser often creates hallucination, i.e., images that have lost the semantics of their originally assigned class, leading to a drop in robustness. Furthermore, its noise-and-denoise procedure introduces a significant distribution shift from the original distribution, causing the denoised smoothing framework to achieve sub-optimal robustness. In this paper, we introduce Fine-Tuning with Confidence-Aware Denoised Image Selection (FT-CADIS), a novel fine-tuning scheme to enhance the certified robustness of off-the-shelf classifiers. FT-CADIS is inspired by the observation that the confidence of off-the-shelf classifiers can effectively identify hallucinated images during denoised smoothing. Based on this, we develop a confidence-aware training objective to handle such hallucinated images and improve the stability of fine-tuning from denoised images. In this way, the classifier can be fine-tuned using only images that are beneficial for adversarial robustness. We also find that such a fine-tuning can be done by updating a small fraction of parameters of the classifier. Extensive experiments demonstrate that FT-CADIS has established the state-of-the-art certified robustness among denoised smoothing methods across all $\ell_2$-adversary radius in various benchmarks.

False data injection attacks (FDIAs) on smart inverters are a growing concern linked to increased renewable energy production. While data-based FDIA detection methods are also actively developed, we show that they remain vulnerable to impactful and stealthy adversarial examples that can be crafted using Reinforcement Learning (RL). We propose to include such adversarial examples in data-based detection training procedure via a continual adversarial RL (CARL) approach. This way, one can pinpoint the deficiencies of data-based detection, thereby offering explainability during their incremental improvement. We show that a continual learning implementation is subject to catastrophic forgetting, and additionally show that forgetting can be addressed by employing a joint training strategy on all generated FDIA scenarios.

Large language models (LLMs) demonstrate remarkable performance across various tasks, prompting researchers to develop diverse evaluation benchmarks. However, existing benchmarks typically measure the ability of LLMs to respond to individual questions, neglecting the complex interactions in real-world applications. In this paper, we introduce Compound Question Synthesis (CQ-Syn) to create the Compound-QA benchmark, focusing on compound questions with multiple sub-questions. This benchmark is derived from existing QA datasets, annotated with proprietary LLMs and verified by humans for accuracy. It encompasses five categories: Factual-Statement, Cause-and-Effect, Hypothetical-Analysis, Comparison-and-Selection, and Evaluation-and-Suggestion. It evaluates the LLM capability in terms of three dimensions including understanding, reasoning, and knowledge. Our assessment of eight open-source LLMs using Compound-QA reveals distinct patterns in their responses to compound questions, which are significantly poorer than those to non-compound questions. Additionally, we investigate various methods to enhance LLMs performance on compound questions. The results indicate that these approaches significantly improve the models' comprehension and reasoning abilities on compound questions.

Bitcoin, launched in 2008 by Satoshi Nakamoto, established a new digital economy where value can be stored and transferred in a fully decentralized manner - alleviating the need for a central authority. This paper introduces a large scale dataset in the form of a transactions graph representing transactions between Bitcoin users along with a set of tasks and baselines. The graph includes 252 million nodes and 785 million edges, covering a time span of nearly 13 years of and 670 million transactions. Each node and edge is timestamped. As for supervised tasks we provide two labeled sets i. a 33,000 nodes based on entity type and ii. nearly 100,000 Bitcoin addresses labeled with an entity name and an entity type. This is the largest publicly available data set of bitcoin transactions designed to facilitate advanced research and exploration in this domain, overcoming the limitations of existing datasets. Various graph neural network models are trained to predict node labels, establishing a baseline for future research. In addition, several use cases are presented to demonstrate the dataset's applicability beyond Bitcoin analysis. Finally, all data and source code is made publicly available to enable reproducibility of the results.

Large language models (LLMs) have excelled in numerous benchmarks, advancing AI applications in both linguistic and non-linguistic tasks. However, this has primarily benefited well-resourced languages, leaving less-resourced ones (LRLs) at a disadvantage. In this paper, we highlight the current state of the NLP field in the specific LRL: kyrgyz tili. Human evaluation, including annotated datasets created by native speakers, remains an irreplaceable component of reliable NLP performance, especially for LRLs where automatic evaluations can fall short. In recent assessments of the resources for Turkic languages, Kyrgyz is labeled with the status 'Scraping By', a severely under-resourced language spoken by millions. This is concerning given the growing importance of the language, not only in Kyrgyzstan but also among diaspora communities where it holds no official status. We review prior efforts in the field, noting that many of the publicly available resources have only recently been developed, with few exceptions beyond dictionaries (the processed data used for the analysis is presented at https://kyrgyznlp.github.io/). While recent papers have made some headway, much more remains to be done. Despite interest and support from both business and government sectors in the Kyrgyz Republic, the situation for Kyrgyz language resources remains challenging. We stress the importance of community-driven efforts to build these resources, ensuring the future advancement sustainability. We then share our view of the most pressing challenges in Kyrgyz NLP. Finally, we propose a roadmap for future development in terms of research topics and language resources.

Allaway and McKeown (2020) categorize stance Argumentation is a pervasive human activity present in various classification into two categories based on the topic: topicphrase aspects of everyday life, which involves expressing and topic-position. For the former, the topic is typically viewpoints backed by reasons or attempting to persuade a noun phrase (including proper noun), such as nuclear others towards a specific perspective (Sobhani, Inkpen, and weapon. For the latter, the topic is a complete position Matwin 2015). In the context of argument mining, a crucial claim such as All countries should give up their nuclear task is argumentative stance classification (Küçük and Can weapons. Notably, the argument we introduce at the beginning 2020), where the goal is to classify an argument's stance as of this section would be classified as favor for the former either favor, against, or neutral regarding a given claim.

There is an urgent need to identify both short and long-term risks from newly emerging types of Artificial Intelligence (AI), as well as available risk management measures. In response, and to support global efforts in regulating AI and writing safety standards, we compile an extensive catalog of risk sources and risk management measures for general-purpose AI (GPAI) systems, complete with descriptions and supporting examples where relevant. This work involves identifying technical, operational, and societal risks across model development, training, and deployment stages, as well as surveying established and experimental methods for managing these risks. To the best of our knowledge, this paper is the first of its kind to provide extensive documentation of both GPAI risk sources and risk management measures that are descriptive, self-contained and neutral with respect to any existing regulatory framework. This work intends to help AI providers, standards experts, researchers, policymakers, and regulators in identifying and mitigating systemic risks from GPAI systems. For this reason, the catalog is released under a public domain license for ease of direct use by stakeholders in AI governance and standards.

Large language models memorize parts of their training data. Memorizing short snippets and facts is required to answer questions about the world and to be fluent in any language. But models have also been shown to reproduce long verbatim sequences of memorized text when prompted by a motivated adversary. In this work, we investigate an intermediate regime of memorization that we call non-adversarial reproduction, where we quantify the overlap between model responses and pretraining data when responding to natural and benign prompts. For a variety of innocuous prompt categories (e.g., writing a letter or a tutorial), we show that up to 15% of the text output by popular conversational language models overlaps with snippets from the Internet. In worst cases, we find generations where 100% of the content can be found exactly online. For the same tasks, we find that human-written text has far less overlap with Internet data. We further study whether prompting strategies can close this reproduction gap between models and humans. While appropriate prompting can reduce non-adversarial reproduction on average, we find that mitigating worst-case reproduction of training data requires stronger defenses -- even for benign interactions.

The integration of intelligent and connected technologies in modern vehicles, while offering enhanced functionalities through Electronic Control Unit and interfaces like OBD-II and telematics, also exposes the vehicle's in-vehicle network (IVN) to potential cyberattacks. In this paper, we consider a specific type of cyberattack known as the injection attack. As demonstrated by empirical data from real-world cybersecurity adversarial competitions(available at https://mimic2024.xctf.org.cn/race/qwmimic2024 ), these injection attacks have excitation effect over time, gradually manipulating network traffic and disrupting the vehicle's normal functioning, ultimately compromising both its stability and safety. To profile the abnormal behavior of attackers, we propose a novel injection attack detector to extract long-term features of attack behavior. Specifically, we first provide a theoretical analysis of modeling the time-excitation effects of the attack using Multi-Dimensional Hawkes Process (MDHP). A gradient descent solver specifically tailored for MDHP, MDHP-GDS, is developed to accurately estimate optimal MDHP parameters. We then propose an injection attack detector, MDHP-Net, which integrates optimal MDHP parameters with MDHP-LSTM blocks to enhance temporal feature extraction. By introducing MDHP parameters, MDHP-Net captures complex temporal features that standard Long Short-Term Memory (LSTM) cannot, enriching temporal dependencies within our customized structure. Extensive evaluations demonstrate the effectiveness of our proposed detection approach.