Federated Learning (FL) enables the utilization of vast, previously inaccessible data sources. At the same time, pre-trained Language Models (LMs) have taken the world by storm and for good reason. They exhibit remarkable emergent abilities and are readily adapted to downstream tasks. This opens one of the most exciting frontiers in FL: fine-tuning LMs. Yet, a persistent challenge in FL is the frequent, rigid communication of parameters -- a problem magnified by the sheer size of these contemporary models. The FedOpt family of algorithms has become the go-to approach for FL, relying on fixed but arbitrary intervals for model exchanges. Recently, the FDA algorithm prescribed a dynamic approach by monitoring the training progress. However, it introduced a hard-to-calibrate parameter and imposed a rigid synchronization scheme. In this work, we address these limitations by proposing the FDA-Opt family of algorithms -- a unified generalization of both FDA and FedOpt. Our experimental evaluation focuses on fine-tuning LMs on downstream NLP tasks and demonstrates that FDA-Opt outperforms FedOpt even when it is configured with hyper-parameters specifically optimized for the latter. In other words, we show that FDA-Opt is a practical, drop-in replacement for FedOpt in modern FL libraries and systems: it requires no additional configuration and delivers superior performance out of the box.

This article unpacks the design choices behind longstanding and newly proposed computational frameworks aimed at finding common grounds across collective preferences and examines their potential future impacts, both technically and normatively. It begins by situating AI-assisted preference elicitation within the historical role of opinion polls, emphasizing that preferences are shaped by the decision-making context and are seldom objectively captured. With that caveat in mind, we explore AI-based democratic innovations as discovery tools for fostering reasonable representations of a collective will, sense-making, and agreement-seeking. At the same time, we caution against dangerously misguided uses, such as enabling binding decisions, fostering gradual disempowerment or post-rationalizing political outcomes.

This position paper argues that large language model (LLM)-based social simulations should establish clear boundaries to meaningfully contribute to social science research. While LLMs offer promising capabilities for modeling human-like agents compared to traditional agent-based modeling, they face fundamental limitations that constrain their reliability for social pattern discovery. The core issue lies in LLMs' tendency towards an ``average persona'' that lacks sufficient behavioral heterogeneity, a critical requirement for simulating complex social dynamics. We examine three key boundary problems: alignment (simulated behaviors matching real-world patterns), consistency (maintaining coherent agent behavior over time), and robustness (reproducibility under varying conditions). We propose heuristic boundaries for determining when LLM-based simulations can reliably advance social science understanding. We believe that these simulations are more valuable when focusing on (1) collective patterns rather than individual trajectories, (2) agent behaviors aligning with real population averages despite limited variance, and (3) proper validation methods available for testing simulation robustness. We provide a practical checklist to guide researchers in determining the appropriate scope and claims for LLM-based social simulations.

For more than a decade now, academicians and online platform administrators have been studying solutions to the problem of bot detection. Bots are computer algorithms whose use is far from being benign: malicious bots are purposely created to distribute spam, sponsor public characters and, ultimately, induce a bias within the public opinion. To fight the bot invasion on our online ecosystem, several approaches have been implemented, mostly based on (supervised and unsupervised) classifiers, which adopt the most varied account features, from the simplest to the most expensive ones to be extracted from the raw data obtainable through the Twitter public APIs. In this exploratory study, using Twitter as a benchmark, we compare the performances of four state-of-art feature sets in detecting novel bots: one of the output scores of the popular bot detector Botometer, which considers more than 1,000 features of an account to take a decision; two feature sets based on the account profile and timeline; and the information about the Twitter client from which the user tweets. The results of our analysis, conducted on six recently released datasets of Twitter accounts, hint at the possible use of general-purpose classifiers and cheap-to-compute account features for the detection of evolved bots.

Road traffic crashes are a significant global cause of fatalities, emphasizing the urgent need for accurate crash data to enhance prevention strategies and inform policy development. This study addresses the challenge of alcohol inference mismatch (AIM) by employing database narrative alignment to identify AIM in crash data. A framework was developed to improve data quality in crash management systems and reduce the percentage of AIM crashes. Utilizing the BERT model, the analysis of 371,062 crash records from Iowa (2016-2022) revealed 2,767 AIM incidents, resulting in an overall AIM percentage of 24.03%. Statistical tools, including the Probit Logit model, were used to explore the crash characteristics affecting AIM patterns. The findings indicate that alcohol-related fatal crashes and nighttime incidents have a lower percentage of the mismatch, while crashes involving unknown vehicle types and older drivers are more susceptible to mismatch. The geospatial cluster as part of this study can identify the regions which have an increased need for education and training. These insights highlight the necessity for targeted training programs and data management teams to improve the accuracy of crash reporting and support evidence-based policymaking.

However, none have considered the dual challenge of attacking both DL-based detection models and triggering the physical relay operation, as is required for attacks on LCDRs. To our knowledge, no prior work investigated the vulnerabilities of DL-based FDIA detection systems in LCDRs against adversarial attacks, despite the critical role LCDRs play in line protection. This problem also encompasses a unique additional set of objectives and constraints that must be taken into consideration to design successful adversarial attacks against the LCDR. For instance, for an adversarial attack to succeed, it must not only deceive the DLS but also trigger the LCDR to trip, adding complexity beyond scenarios where decision-making relies solely on a machine-learning model. Herein, the adversarial samples must be misclassified by the DLS as faults, since the primary objective of the attacker is to cause the LCDR to trip unnecessarily in the absence of a real fault. Moreover, the problem is constrained by the requirement that only features from remote measurements can be manipulated, while local measurement features remain unchanged. Local measurements, being closely tied to the relay, are difficult to manipulate as they are transmitted directly through copper wires, whereas remote measurements, which traverse longer distances and potentially vulnerable media, offer a broader attack surface. This distinction highlights the need for robust detection systems capable of withstanding targeted adversarial attacks. Finally, for LCDRs, these robust detection systems must not negatively impact the LCDR's ability to detect actual faults.

Prompt injection threatens novel applications that emerge from adapting LLMs for various user tasks. The newly developed LLM-based software applications become more ubiquitous and diverse. However, the threat of prompt injection attacks undermines the security of these systems as the mitigation and defenses against them, proposed so far, are insufficient. We investigated the capabilities of early prompt injection detection systems, focusing specifically on the detection performance of techniques implemented in various open-source solutions. These solutions are supposed to detect certain types of prompt injection attacks, including the prompt leak. In prompt leakage attacks, an attacker maliciously manipulates the LLM into outputting its system instructions, violating the system's confidentiality. Our study presents analyzes of distinct prompt leakage detection techniques, and a comparative analysis of several detection solutions, which implement those techniques. We identify the strengths and weaknesses of these techniques and elaborate on their optimal configuration and usage in high-stake deployments. In one of the first studies on existing prompt leak detection solutions, we compared the performances of LLM Guard, Vigil, and Rebuff. We concluded that the implementations of canary word checks in Vigil and Rebuff were not effective at detecting prompt leak attacks, and we proposed improvements for them. We also found an evasion weakness in Rebuff's secondary model-based technique and proposed a mitigation. Then, the result of the comparison of LLM Guard, Vigil, and Rebuff at their peak performance revealed that Vigil is optimal for cases when minimal false positive rate is required, and Rebuff is the most optimal for average needs.

The rapid growth of AI, data-intensive science, and digital twin technologies has driven an unprecedented demand for high-performance computing (HPC) across the research ecosystem. While national laboratories and industrial hyperscalers have invested heavily in exascale and GPU-centric architectures, university-operated HPC systems remain comparatively under-resourced. This survey presents a comprehensive assessment of the HPC landscape across U.S. universities, benchmarking their capabilities against Department of Energy (DOE) leadership-class systems and industrial AI infrastructures. We examine over 50 premier research institutions, analyzing compute capacity, architectural design, governance models, and energy efficiency. Our findings reveal that university clusters, though vital for academic research, exhibit significantly lower growth trajectories (CAGR $\approx$ 18%) than their national ($\approx$ 43%) and industrial ($\approx$ 78%) counterparts. The increasing skew toward GPU-dense AI workloads has widened the capability gap, highlighting the need for federated computing, idle-GPU harvesting, and cost-sharing models. We also identify emerging paradigms, such as decentralized reinforcement learning, as promising opportunities for democratizing AI training within campus environments. Ultimately, this work provides actionable insights for academic leaders, funding agencies, and technology partners to ensure more equitable and sustainable HPC access in support of national research priorities.

In this work, we investigate how autonomous agents, organized into tribes, learn to use communication signals to coordinate their activities and enhance their collective efficiency. Using the NEC-DAC (Neurally Encoded Culture - Distributed Autonomous Communicators) system, where each agent is equipped with its own neural network for decision-making, we demonstrate how these agents develop a shared behavioral system -- akin to a culture -- through learning and signalling. Our research focuses on the self-organization of culture within these tribes of agents and how varying communication strategies impact their fitness and cooperation. By analyzing different social structures, such as authority hierarchies, we show that the culture of cooperation significantly influences the tribe's performance. Furthermore, we explore how signals not only facilitate the emergence of culture but also enable its transmission across generations of agents. Additionally, we examine the benefits of coordinating behavior and signaling within individual agents' neural networks.

This work has been accepted for publication in the IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). The final version will be available on IEEE Xplore. Abstract --State-of-the-art convolutional neural network models for object detection and image classification are vulnerable to physically realizable adversarial perturbations, such as patch attacks. Existing defenses have focused, implicitly or explicitly, on single-patch attacks, leaving their sensitivity to the number of patches as an open question or rendering them computationally infeasible or inefficient against attacks consisting of multiple patches in the worst cases. In this work, we propose SpaNN, an attack detector whose computational complexity is independent of the expected number of adversarial patches. The key novelty of the proposed detector is that it builds an ensemble of binarized feature maps by applying a set of saliency thresholds to the neural activations of the first convolutional layer of the victim model. It then performs clustering on the ensemble and uses the cluster features as the input to a classifier for attack detection. Contrary to existing detectors, SpaNN does not rely on a fixed saliency threshold for identifying adversarial regions, which makes it robust against white box adversarial attacks. We evaluate SpaNN on four widely used data sets for object detection and classification, and our results show that SpaNN outperforms state-of-the-art defenses by up to 11 and 27 percentage points in the case of object detection and the case of image classification, respectively. Our code is available at https://github.com/gerkbyrd/SpaNN . Deep learning models achieve state-of-the-art performance on computer vision tasks, but they are vulnerable to adversarial attacks, i.e., input perturbations crafted to change the model's output [1]-[3]. Several digital attack generation methods have been proposed in the past decade [1], [4]-[6], followed by corresponding defense schemes [7]-[10]. These attacks assume the adversary has direct access to the pixels of the input image provided to the model. In more recent years, focus has shifted towards physically realizable attacks [11]. They differ from digital attacks in that they are spatially constrained, and they typically involve applying a printable patch containing an adversarial pattern to an object in the physical scene.