Deep neural networks (NNs) for computer vision are vulnerable to adversarial attacks, i.e., miniscule malicious changes to inputs may induce unintuitive outputs. One key approach to verify and mitigate such robustness issues is to falsify expected output behavior. This allows, e.g., to locally proof security, or to (re)train NNs on obtained adversarial input examples. Due to the black-box nature of NNs, current attacks only falsify a class of the final output, such as flipping from $\texttt{stop_sign}$ to $\neg\texttt{stop_sign}$. In this short position paper we generalize this to search for generally illogical behavior, as considered in NN verification: falsify constraints (concept-based properties) involving further human-interpretable concepts, like $\texttt{red}\wedge\texttt{octogonal}\rightarrow\texttt{stop_sign}$. For this, an easy implementation of concept-based properties on already trained NNs is proposed using techniques from explainable artificial intelligence. Further, we sketch the theoretical proof that attacks on concept-based properties are expected to have a reduced search space compared to simple class falsification, whilst arguably be more aligned with intuitive robustness targets. As an outlook to this work in progress we hypothesize that this approach has potential to efficiently and simultaneously improve logical compliance and robustness.

We study transformer language models, analyzing attention heads whose attention patterns are spread out, and whose attention scores depend weakly on content. We argue that the softmax denominators of these heads are stable when the underlying token distribution is fixed. By sampling softmax denominators from a "calibration text", we can combine together the outputs of multiple such stable heads in the first layer of GPT2-Small, approximating their combined output by a linear summary of the surrounding text. This approximation enables a procedure where from the weights alone - and a single calibration text - we can uncover hundreds of first layer neurons that respond to high-level contextual properties of the surrounding text, including neurons that didn't activate on the calibration text.

Ensuring the safety of vulnerable road users (VRUs), such as pedestrians and cyclists, remains a critical global challenge, as conventional infrastructure-based measures often prove inadequate in dynamic urban environments. Recent advances in artificial intelligence (AI), particularly in visual perception and reasoning, open new opportunities for proactive and context-aware VRU protection. However, existing surveys on AI applications for VRUs predominantly focus on detection, offering limited coverage of other vision-based tasks that are essential for comprehensive VRU understanding and protection. This paper presents a state-of-the-art review of recent progress in camera-based AI sensing systems for VRU safety, with an emphasis on developments from the past five years and emerging research trends. We systematically examine four core tasks, namely detection and classification, tracking and reidentification, trajectory prediction, and intent recognition and prediction, which together form the backbone of AI-empowered proactive solutions for VRU protection in intelligent transportation systems. To guide future research, we highlight four major open challenges from the perspectives of data, model, and deployment. By linking advances in visual AI with practical considerations for real-world implementation, this survey aims to provide a foundational reference for the development of next-generation sensing systems to enhance VRU safety.

Climate anomalies significantly impact terrestrial carbon cycle dynamics, necessitating robust methods for detecting and analyzing anomalous behavior in plant productivity. This study presents a novel application of variational autoencoders (VAE) for identifying extreme events in gross primary productivity (GPP) from Community Earth System Model version 2 simulations across four AR6 regions in the Continental United States. We compare VAE-based anomaly detection with traditional singular spectral analysis (SSA) methods across three time periods: 1850-80, 1950-80, and 2050-80 under the SSP585 scenario. The VAE architecture employs three dense layers and a latent space with an input sequence length of 12 months, trained on a normalized GPP time series to reconstruct the GPP and identifying anomalies based on reconstruction errors. Extreme events are defined using 5th percentile thresholds applied to both VAE and SSA anomalies. Results demonstrate strong regional agreement between VAE and SSA methods in spatial patterns of extreme event frequencies, despite VAE producing higher threshold values (179-756 GgC for VAE vs. 100-784 GgC for SSA across regions and periods). Both methods reveal increasing magnitudes and frequencies of negative carbon cycle extremes toward 2050-80, particularly in Western and Central North America. The VAE approach shows comparable performance to established SSA techniques, while offering computational advantages and enhanced capability for capturing non-linear temporal dependencies in carbon cycle variability. Unlike SSA, the VAE method does not require one to define the periodicity of the signals in the data; it discovers them from the data.

Adversarial machine learning considers the exploitable vulnerabilities of machine learning models and the strategies needed to counter or mitigate such threats [32]. By considering these vulnerabilities during the development stage of our machine learning models, we can work to build resilient methods [9, 11] such as protection from credit card fraud [35] or finding the optimal placement of air defence systems [20]. In particular, we consider the model's sensitivity to changes in the distribution of the data. The way the adversary influences the distribution can fall under numerous categories, see [21] for a helpful taxonomy that categorises these attacks. We focus on the specific case of exploratory attacks, which consider the scenarios where adversaries attempt to modify their data to evade detection by a classifier. Such attacks might occur in security scenarios such as malware detection [3] and network intrusion traffic [31]. In a similar vein, and more recently, vulnerabilities in deep neural networks (DNN) are being discovered, particularly in the field of computer vision and image classification; small perturbations in the data can lead to incorrect classifications by the DNN [33, 19]. These vulnerabilities raise concerns about the robustness of the machine learning technology that is being adopted and, in some cases, in how safe relying on their predictions could be in high-risk scenarios such as autonomous driving [15] and medical diagnosis [16]. By modelling the adversary's behaviour and anticipating these attacks, we can train classifiers that are resilient to such changes in the distribution before they occur.

Foundation models (FMs) deployed in real-world tasks such as computer-use agents must integrate diverse modalities. How good are FMs at performing joint reasoning, simultaneously reasoning over multiple modalities, especially when the modalities interact and relate to each other to form cross-modal context? To better understand this problem, we study FMs on cross-modal conflicts: scenarios where conflicting evidence is presented across modalities. This allows us to examine whether FMs prioritize one modality over another or reason jointly to reconcile the conflict. Our experiments reveal that FMs can recognize conflicts in unimodal contexts, composed of a single modality, 90% of the time, but the ratio falls as low as 3% when evidence is split across modalities -- similar observations hold in cross-lingual contexts, composed of multiple languages. We trace this failure to cross-modal attention imbalance, showing that FMs exhibit extreme asymmetry in attention scores, disproportionately prioritizing certain modalities. We show that cross-modal attention imbalance does not go away by simply scaling up multimodal or multilingual datasets blindly, since they lack training examples that explicitly require cross-modal reasoning. We demonstrate that even a simple and scalable method of explicitly combining multiple modalities within each training instance significantly reduces attention imbalance. Reduced attention imbalance directly translates to improved downstream performance on several vision-language benchmarks. Our findings underscore the importance of systematically addressing cross-modal contexts to build reliable foundation models.

Claim verification with large language models (LLMs) has recently attracted growing attention, due to their strong reasoning capabilities and transparent verification processes compared to traditional answer-only judgments. However, existing approaches to online claim verification, which requires iterative evidence retrieval and reasoning, still mainly rely on prompt engineering or pre-designed reasoning workflows, without unified training to improve necessary skills. Therefore, we introduce Veri-R1, an online reinforcement learning (RL) framework that enables an LLM to interact with a search engine and to receive reward signals that explicitly shape its planning, retrieval, and reasoning behaviors. This dynamic interaction of LLM with retrieval systems more accurately reflects real-world verification scenarios and fosters comprehensive verification skills. Empirical results show that Veri-R1 improves joint accuracy by up to 30% and doubles the evidence score, often surpassing its larger-scale model counterparts. Ablation studies further reveal the impact of reward components, and the link between output logits and label accuracy. Our results highlight the effectiveness of online RL for precise and faithful claim verification, providing an important foundation for future research. We release our code to support community progress in LLM empowered claim verification.

Political beliefs vary significantly across different countries, reflecting distinct historical, cultural, and institutional contexts. These ideologies, ranging from liberal democracies to rigid autocracies, influence human societies, as well as the digital systems that are constructed within those societies. The advent of generative artificial intelligence, particularly Large Language Models (LLMs), introduces new agents in the political space-agents trained on massive corpora that replicate and proliferate socio-political assumptions. This paper analyses whether LLMs display propensities consistent with democratic or autocratic world-views. We validate this insight through experimental tests in which we experiment with the leading LLMs developed across disparate political contexts, using several existing psychometric and political orientation measures. The analysis is based on both numerical scoring and qualitative analysis of the models' responses. Findings indicate high model-to-model variability and a strong association with the political culture of the country in which the model was developed. These findings highlight the need for more detailed examination of the socio-political dimensions embedded within AI systems.

We examine how textual features in earnings press releases predict stock returns on earnings announcement days. Using over 138,000 press releases from 2005 to 2023, we compare traditional bag-of-words and BERT-based embeddings. We find that press release content (soft information) is as informative as earnings surprise (hard information), with FinBERT yielding the highest predictive power. Combining models enhances explanatory strength and interpretability of the content of press releases. Stock prices fully reflect the content of press releases at market open. If press releases are leaked, it offers predictive advantage. Topic analysis reveals self-serving bias in managerial narratives. Our framework supports real-time return prediction through the integration of online learning, provides interpretability and reveals the nuanced role of language in price formation.

We address the challenge of generating diverse attack prompts for large language models (LLMs) that elicit harmful behaviors (e.g., insults, sexual content) and are used for safety fine-tuning. Rather than relying on manual prompt engineering, attacker LLMs can be trained with reinforcement learning (RL) to automatically generate such prompts using only a toxicity classifier as a reward. However, capturing a wide range of harmful behaviors is a significant challenge that requires explicit diversity objectives. Existing diversity-seeking RL methods often collapse to limited modes: once high-reward prompts are found, exploration of new regions is discouraged. Inspired by the active learning paradigm that encourages adaptive exploration, we introduce \textit{Active Attacks}, a novel RL-based red-teaming algorithm that adapts its attacks as the victim evolves. By periodically safety fine-tuning the victim LLM with collected attack prompts, rewards in exploited regions diminish, which forces the attacker to seek unexplored vulnerabilities. This process naturally induces an easy-to-hard exploration curriculum, where the attacker progresses beyond easy modes toward increasingly difficult ones. As a result, Active Attacks uncovers a wide range of local attack modes step by step, and their combination achieves wide coverage of the multi-mode distribution. Active Attacks, a simple plug-and-play module that seamlessly integrates into existing RL objectives, unexpectedly outperformed prior RL-based methods -- including GFlowNets, PPO, and REINFORCE -- by improving cross-attack success rates against GFlowNets, the previous state-of-the-art, from 0.07% to 31.28% (a relative gain greater than $400\ \times$) with only a 6% increase in computation. Our code is publicly available \href{https://github.com/dbsxodud-11/active_attacks}{here}.